asahi417/seamless-align-enA-zhA
收藏Hugging Face2024-06-10 更新2024-06-12 收录
下载链接:
https://hf-mirror.com/datasets/asahi417/seamless-align-enA-zhA
下载链接
链接失效反馈官方服务:
资源简介:
---
dataset_info:
- config_name: subset_1
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 319739170.7
num_examples: 1975
download_size: 310664733
dataset_size: 319739170.7
- config_name: subset_10
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 298109697.895
num_examples: 2051
download_size: 287323026
dataset_size: 298109697.895
- config_name: subset_100
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 294538076.966
num_examples: 1899
download_size: 298561676
dataset_size: 294538076.966
- config_name: subset_101
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 295117175.227
num_examples: 1889
download_size: 296415225
dataset_size: 295117175.227
- config_name: subset_102
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 290304385.088
num_examples: 1872
download_size: 288588323
dataset_size: 290304385.088
- config_name: subset_103
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 299658559.27
num_examples: 1870
download_size: 292012870
dataset_size: 299658559.27
- config_name: subset_104
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 291704919.932
num_examples: 1883
download_size: 291567753
dataset_size: 291704919.932
- config_name: subset_105
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 301728156.733
num_examples: 1879
download_size: 296657748
dataset_size: 301728156.733
- config_name: subset_106
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 285432700.842
num_examples: 1874
download_size: 280522644
dataset_size: 285432700.842
- config_name: subset_107
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 288872679.1
num_examples: 1845
download_size: 281612500
dataset_size: 288872679.1
- config_name: subset_108
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 293446909.248
num_examples: 1874
download_size: 295564686
dataset_size: 293446909.248
- config_name: subset_109
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 296033533.472
num_examples: 1874
download_size: 292777579
dataset_size: 296033533.472
- config_name: subset_11
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 283024909.432
num_examples: 2004
download_size: 280966664
dataset_size: 283024909.432
- config_name: subset_110
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 290291487.248
num_examples: 1852
download_size: 283892479
dataset_size: 290291487.248
- config_name: subset_111
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 291219914.025
num_examples: 1865
download_size: 290589194
dataset_size: 291219914.025
- config_name: subset_112
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 288740805.936
num_examples: 1856
download_size: 288475243
dataset_size: 288740805.936
- config_name: subset_113
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 289351970.7
num_examples: 1850
download_size: 285944643
dataset_size: 289351970.7
- config_name: subset_114
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 292161120.119
num_examples: 1861
download_size: 294186516
dataset_size: 292161120.119
- config_name: subset_115
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 292653119.782
num_examples: 1834
download_size: 291721313
dataset_size: 292653119.782
- config_name: subset_116
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 283096777.855
num_examples: 1849
download_size: 289361158
dataset_size: 283096777.855
- config_name: subset_117
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 293881087.348
num_examples: 1866
download_size: 292839103
dataset_size: 293881087.348
- config_name: subset_118
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 291572847.082
num_examples: 1827
download_size: 285560287
dataset_size: 291572847.082
- config_name: subset_119
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 286442218.965
num_examples: 1835
download_size: 288215677
dataset_size: 286442218.965
- config_name: subset_12
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 290129007.791
num_examples: 2047
download_size: 280920831
dataset_size: 290129007.791
- config_name: subset_120
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 291331290.072
num_examples: 1846
download_size: 286097533
dataset_size: 291331290.072
- config_name: subset_121
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 297703955.03
num_examples: 1845
download_size: 291473639
dataset_size: 297703955.03
- config_name: subset_122
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 279906476.545
num_examples: 1831
download_size: 285475884
dataset_size: 279906476.545
- config_name: subset_123
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 289757063.076
num_examples: 1814
download_size: 287979933
dataset_size: 289757063.076
- config_name: subset_124
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 298196705.384
num_examples: 1838
download_size: 293635004
dataset_size: 298196705.384
- config_name: subset_125
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 296169995.06
num_examples: 1865
download_size: 296042317
dataset_size: 296169995.06
- config_name: subset_126
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 298136887.655
num_examples: 1895
download_size: 302010240
dataset_size: 298136887.655
- config_name: subset_127
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 289720257.861
num_examples: 1839
download_size: 290456289
dataset_size: 289720257.861
- config_name: subset_128
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 302632358.952
num_examples: 1848
download_size: 297357826
dataset_size: 302632358.952
- config_name: subset_129
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 304624749.166
num_examples: 1894
download_size: 300735539
dataset_size: 304624749.166
- config_name: subset_13
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 278484276.254
num_examples: 2029
download_size: 280165390
dataset_size: 278484276.254
- config_name: subset_130
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 289480118.858
num_examples: 1833
download_size: 292242936
dataset_size: 289480118.858
- config_name: subset_131
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 294145073.631
num_examples: 1821
download_size: 292465902
dataset_size: 294145073.631
- config_name: subset_132
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 301310469.492
num_examples: 1876
download_size: 301684110
dataset_size: 301310469.492
- config_name: subset_133
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 300286777.635
num_examples: 1853
download_size: 292527545
dataset_size: 300286777.635
- config_name: subset_134
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 294898657.934
num_examples: 1839
download_size: 291599684
dataset_size: 294898657.934
- config_name: subset_135
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 308476505.09
num_examples: 1870
download_size: 303323139
dataset_size: 308476505.09
- config_name: subset_136
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 298371772.224
num_examples: 1894
download_size: 297692805
dataset_size: 298371772.224
- config_name: subset_137
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 293874571.076
num_examples: 1844
download_size: 291427310
dataset_size: 293874571.076
- config_name: subset_138
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 301342315.96
num_examples: 1880
download_size: 300904584
dataset_size: 301342315.96
- config_name: subset_139
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 295027014.92
num_examples: 1841
download_size: 294054919
dataset_size: 295027014.92
- config_name: subset_14
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 286646552.664
num_examples: 2021
download_size: 282237812
dataset_size: 286646552.664
- config_name: subset_140
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 292976600.634
num_examples: 1823
download_size: 292666649
dataset_size: 292976600.634
- config_name: subset_141
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 289724725.211
num_examples: 1829
download_size: 289524845
dataset_size: 289724725.211
- config_name: subset_142
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 297433526.16
num_examples: 1856
download_size: 296322915
dataset_size: 297433526.16
- config_name: subset_143
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 288807477.128
num_examples: 1804
download_size: 288339515
dataset_size: 288807477.128
- config_name: subset_144
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 298625850.782
num_examples: 1862
download_size: 299067675
dataset_size: 298625850.782
- config_name: subset_145
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 304919995.364
num_examples: 1858
download_size: 298551896
dataset_size: 304919995.364
- config_name: subset_146
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 299881041.288
num_examples: 1857
download_size: 299749125
dataset_size: 299881041.288
- config_name: subset_147
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 297835062.66
num_examples: 1862
download_size: 293681315
dataset_size: 297835062.66
- config_name: subset_148
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 301579172.16
num_examples: 1858
download_size: 296804556
dataset_size: 301579172.16
- config_name: subset_149
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 297518688.632
num_examples: 1884
download_size: 297167964
dataset_size: 297518688.632
- config_name: subset_15
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 283494967.61
num_examples: 2018
download_size: 281062159
dataset_size: 283494967.61
- config_name: subset_150
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 305530316.848
num_examples: 1874
download_size: 304862222
dataset_size: 305530316.848
- config_name: subset_151
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 298254709.99
num_examples: 1874
download_size: 299362404
dataset_size: 298254709.99
- config_name: subset_152
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 297507789.876
num_examples: 1837
download_size: 297461506
dataset_size: 297507789.876
- config_name: subset_153
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 305471175.151
num_examples: 1873
download_size: 304122959
dataset_size: 305471175.151
- config_name: subset_154
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 305010379.992
num_examples: 1872
download_size: 303689206
dataset_size: 305010379.992
- config_name: subset_155
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 297939968.46
num_examples: 1835
download_size: 294966361
dataset_size: 297939968.46
- config_name: subset_156
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 297631112.117
num_examples: 1843
download_size: 296548773
dataset_size: 297631112.117
- config_name: subset_157
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 308284252.976
num_examples: 1872
download_size: 304930394
dataset_size: 308284252.976
- config_name: subset_158
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 296675082.43
num_examples: 1790
download_size: 295525351
dataset_size: 296675082.43
- config_name: subset_159
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 274701564.18
num_examples: 1668
download_size: 273897598
dataset_size: 274701564.18
- config_name: subset_16
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 275411567.982
num_examples: 1982
download_size: 269455591
dataset_size: 275411567.982
- config_name: subset_160
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 306077929.05
num_examples: 1850
download_size: 303164419
dataset_size: 306077929.05
- config_name: subset_161
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 295970261.192
num_examples: 1843
download_size: 292979658
dataset_size: 295970261.192
- config_name: subset_162
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 299334312.804
num_examples: 1862
download_size: 302840010
dataset_size: 299334312.804
- config_name: subset_163
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 309624660.23
num_examples: 1870
download_size: 300619438
dataset_size: 309624660.23
- config_name: subset_164
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 311502860.318
num_examples: 1846
download_size: 304602854
dataset_size: 311502860.318
- config_name: subset_165
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 635753732.613
num_examples: 1847
download_size: 469830966
dataset_size: 635753732.613
- config_name: subset_166
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 295286386.928
num_examples: 1878
download_size: 301259289
dataset_size: 295286386.928
- config_name: subset_167
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 307622359.795
num_examples: 1867
download_size: 302793761
dataset_size: 307622359.795
- config_name: subset_168
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 309783418.708
num_examples: 1882
download_size: 310111282
dataset_size: 309783418.708
- config_name: subset_169
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 318616304.412
num_examples: 1858
download_size: 308497819
dataset_size: 318616304.412
- config_name: subset_17
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 274932661.517
num_examples: 2017
download_size: 269785533
dataset_size: 274932661.517
- config_name: subset_170
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 312070150.912
num_examples: 1886
download_size: 307881984
dataset_size: 312070150.912
- config_name: subset_171
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 306364367.069
num_examples: 1869
download_size: 304177383
dataset_size: 306364367.069
- config_name: subset_172
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 308592472.1
num_examples: 1850
download_size: 307381935
dataset_size: 308592472.1
- config_name: subset_173
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 299402675.782
num_examples: 1858
download_size: 299419584
dataset_size: 299402675.782
- config_name: subset_174
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 300563374.906
num_examples: 1842
download_size: 297648499
dataset_size: 300563374.906
- config_name: subset_175
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 301719227.275
num_examples: 1845
download_size: 300727251
dataset_size: 301719227.275
- config_name: subset_176
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 306991676.447
num_examples: 1821
download_size: 301434625
dataset_size: 306991676.447
- config_name: subset_177
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 303664581.793
num_examples: 1849
download_size: 297580206
dataset_size: 303664581.793
- config_name: subset_178
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 309527932.92
num_examples: 1880
download_size: 309409752
dataset_size: 309527932.92
- config_name: subset_179
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 310462189.276
num_examples: 1876
download_size: 307333068
dataset_size: 310462189.276
- config_name: subset_18
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 268181749.251
num_examples: 1949
download_size: 266996778
dataset_size: 268181749.251
- config_name: subset_180
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 310760544.062
num_examples: 1909
download_size: 307822437
dataset_size: 310760544.062
- config_name: subset_181
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 309413580.256
num_examples: 1866
download_size: 305962443
dataset_size: 309413580.256
- config_name: subset_182
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 310487425.795
num_examples: 1865
download_size: 309678990
dataset_size: 310487425.795
- config_name: subset_183
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 304814932.496
num_examples: 1844
download_size: 306217263
dataset_size: 304814932.496
- config_name: subset_184
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 306250790.283
num_examples: 1841
download_size: 305659345
dataset_size: 306250790.283
- config_name: subset_185
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 302859024.684
num_examples: 1836
download_size: 304485714
dataset_size: 302859024.684
- config_name: subset_186
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 308149512.956
num_examples: 1862
download_size: 307556460
dataset_size: 308149512.956
- config_name: subset_187
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 304259071.519
num_examples: 1843
download_size: 303287621
dataset_size: 304259071.519
- config_name: subset_188
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 301193628.55
num_examples: 1846
download_size: 301707842
dataset_size: 301193628.55
- config_name: subset_189
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 310413049.278
num_examples: 1886
download_size: 310853471
dataset_size: 310413049.278
- config_name: subset_19
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 280933275.176
num_examples: 1996
download_size: 273325675
dataset_size: 280933275.176
- config_name: subset_190
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 305588896.225
num_examples: 1865
download_size: 303727464
dataset_size: 305588896.225
- config_name: subset_191
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 309076206.924
num_examples: 1858
download_size: 315793640
dataset_size: 309076206.924
- config_name: subset_192
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 308107332.837
num_examples: 1857
download_size: 309860837
dataset_size: 308107332.837
- config_name: subset_193
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 304228895.54
num_examples: 1860
download_size: 304664827
dataset_size: 304228895.54
- config_name: subset_194
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 307074611.338
num_examples: 1839
download_size: 304119418
dataset_size: 307074611.338
- config_name: subset_195
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 313623630.734
num_examples: 1857
download_size: 306322761
dataset_size: 313623630.734
- config_name: subset_196
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 312395375.73
num_examples: 1871
download_size: 311576983
dataset_size: 312395375.73
- config_name: subset_197
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 310978589.208
num_examples: 1896
download_size: 307203426
dataset_size: 310978589.208
- config_name: subset_198
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 307839555.926
num_examples: 1869
download_size: 309760841
dataset_size: 307839555.926
- config_name: subset_199
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 304231609.397
num_examples: 1857
download_size: 306457196
dataset_size: 304231609.397
- config_name: subset_2
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 320605270.138
num_examples: 2066
download_size: 321369953
dataset_size: 320605270.138
- config_name: subset_20
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 270630715.338
num_examples: 1967
download_size: 271563849
dataset_size: 270630715.338
- config_name: subset_200
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 314579540.708
num_examples: 1879
download_size: 310408752
dataset_size: 314579540.708
- config_name: subset_201
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 296338445.17
num_examples: 1810
download_size: 295373811
dataset_size: 296338445.17
- config_name: subset_202
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 319710820.712
num_examples: 1896
download_size: 322696681
dataset_size: 319710820.712
- config_name: subset_203
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 310174841.25
num_examples: 1875
download_size: 308103197
dataset_size: 310174841.25
- config_name: subset_204
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 306119465.26
num_examples: 1854
download_size: 306806496
dataset_size: 306119465.26
- config_name: subset_205
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 315915954.165
num_examples: 1865
download_size: 310006696
dataset_size: 315915954.165
- config_name: subset_206
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 310683860.1
num_examples: 1850
download_size: 306724973
dataset_size: 310683860.1
- config_name: subset_207
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 298214038.088
num_examples: 1863
download_size: 302102249
dataset_size: 298214038.088
- config_name: subset_208
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 303787581.89
num_examples: 1830
download_size: 306966502
dataset_size: 303787581.89
- config_name: subset_209
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 303197800.868
num_examples: 1822
download_size: 301848955
dataset_size: 303197800.868
- config_name: subset_21
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 274503412.815
num_examples: 1945
download_size: 265958127
dataset_size: 274503412.815
- config_name: subset_210
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 310314065.883
num_examples: 1871
download_size: 311769567
dataset_size: 310314065.883
- config_name: subset_211
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 312623505.648
num_examples: 1864
download_size: 310892743
dataset_size: 312623505.648
- config_name: subset_212
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 313076207.936
num_examples: 1834
download_size: 312433773
dataset_size: 313076207.936
- config_name: subset_213
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 306514798.055
num_examples: 1835
download_size: 309112272
dataset_size: 306514798.055
- config_name: subset_214
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 296742615.344
num_examples: 1866
download_size: 301788085
dataset_size: 296742615.344
- config_name: subset_215
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 312947181.783
num_examples: 1871
download_size: 309609936
dataset_size: 312947181.783
- config_name: subset_216
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 307671250.735
num_examples: 1851
download_size: 306532994
dataset_size: 307671250.735
- config_name: subset_217
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 314046020.064
num_examples: 1858
download_size: 307531539
dataset_size: 314046020.064
- config_name: subset_218
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 310977766.55
num_examples: 1858
download_size: 310732616
dataset_size: 310977766.55
- config_name: subset_219
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 313640863.872
num_examples: 1846
download_size: 308662003
dataset_size: 313640863.872
- config_name: subset_22
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 264633816.522
num_examples: 1929
download_size: 264616971
dataset_size: 264633816.522
- config_name: subset_220
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 315426591.757
num_examples: 1849
download_size: 309308500
dataset_size: 315426591.757
- config_name: subset_221
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 310825983.942
num_examples: 1831
download_size: 306845005
dataset_size: 310825983.942
- config_name: subset_222
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 301463529.8
num_examples: 1840
download_size: 302651669
dataset_size: 301463529.8
- config_name: subset_223
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 304434694.25
num_examples: 1825
download_size: 299977061
dataset_size: 304434694.25
- config_name: subset_224
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 318584293.894
num_examples: 1878
download_size: 314749210
dataset_size: 318584293.894
- config_name: subset_225
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 306321065.25
num_examples: 1850
download_size: 303836496
dataset_size: 306321065.25
- config_name: subset_226
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 317356628.286
num_examples: 1886
download_size: 318288340
dataset_size: 317356628.286
- config_name: subset_227
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 306935287.184
num_examples: 1836
download_size: 309492817
dataset_size: 306935287.184
- config_name: subset_228
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 305329165.728
num_examples: 1842
download_size: 307913676
dataset_size: 305329165.728
- config_name: subset_229
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 306287032.42
num_examples: 1805
download_size: 306980175
dataset_size: 306287032.42
- config_name: subset_23
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 274735810.932
num_examples: 1966
download_size: 270761022
dataset_size: 274735810.932
- config_name: subset_230
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 325539848.552
num_examples: 1872
download_size: 324189898
dataset_size: 325539848.552
- config_name: subset_231
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 319989566.588
num_examples: 1879
download_size: 315109155
dataset_size: 319989566.588
- config_name: subset_232
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 311590621.997
num_examples: 1857
download_size: 310091246
dataset_size: 311590621.997
- config_name: subset_233
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 305548640.472
num_examples: 1872
download_size: 307828694
dataset_size: 305548640.472
- config_name: subset_234
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 322864261.585
num_examples: 1895
download_size: 318421128
dataset_size: 322864261.585
- config_name: subset_235
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 316398329.434
num_examples: 1867
download_size: 312802597
dataset_size: 316398329.434
- config_name: subset_236
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 309727964.158
num_examples: 1862
download_size: 312614772
dataset_size: 309727964.158
- config_name: subset_237
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 314955489.694
num_examples: 1846
download_size: 315363953
dataset_size: 314955489.694
- config_name: subset_238
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 311550628.616
num_examples: 1873
download_size: 314343160
dataset_size: 311550628.616
- config_name: subset_239
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 316111803.456
num_examples: 1868
download_size: 316174604
dataset_size: 316111803.456
- config_name: subset_24
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 263557442.739
num_examples: 1927
download_size: 264402483
dataset_size: 263557442.739
- config_name: subset_240
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 304309872.42
num_examples: 1820
download_size: 304478392
dataset_size: 304309872.42
- config_name: subset_241
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 318461279.184
num_examples: 1888
download_size: 318409489
dataset_size: 318461279.184
- config_name: subset_242
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 313183711.776
num_examples: 1849
download_size: 308058687
dataset_size: 313183711.776
- config_name: subset_243
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 316444162.096
num_examples: 1856
download_size: 315888630
dataset_size: 316444162.096
- config_name: subset_244
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 302269084.236
num_examples: 1831
download_size: 303808373
dataset_size: 302269084.236
- config_name: subset_245
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 315164005.951
num_examples: 1841
download_size: 312736546
dataset_size: 315164005.951
- config_name: subset_246
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 305596540.204
num_examples: 1852
download_size: 309823437
dataset_size: 305596540.204
- config_name: subset_247
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 306969803.02
num_examples: 1870
download_size: 312978126
dataset_size: 306969803.02
- config_name: subset_248
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 302553854.724
num_examples: 1828
download_size: 302606973
dataset_size: 302553854.724
- config_name: subset_249
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 313294938.55
num_examples: 1850
download_size: 312216239
dataset_size: 313294938.55
- config_name: subset_25
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 277442943.442
num_examples: 1938
download_size: 271944723
dataset_size: 277442943.442
- config_name: subset_250
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 315001588.569
num_examples: 1863
download_size: 308113702
dataset_size: 315001588.569
- config_name: subset_251
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 312726012.788
num_examples: 1852
download_size: 318269903
dataset_size: 312726012.788
- config_name: subset_252
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 324657673.39
num_examples: 1845
download_size: 317723333
dataset_size: 324657673.39
- config_name: subset_253
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 317071706.428
num_examples: 1868
download_size: 322004916
dataset_size: 317071706.428
- config_name: subset_254
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 309957109.819
num_examples: 1839
download_size: 309525244
dataset_size: 309957109.819
- config_name: subset_255
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 325881097.88
num_examples: 1830
download_size: 318794842
dataset_size: 325881097.88
- config_name: subset_256
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 306411040.775
num_examples: 1817
download_size: 304499992
dataset_size: 306411040.775
- config_name: subset_257
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 316194668.276
num_examples: 1853
download_size: 319148742
dataset_size: 316194668.276
- config_name: subset_258
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 263090662.544
num_examples: 1541
download_size: 261129453
dataset_size: 263090662.544
- config_name: subset_26
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 252672361.032
num_examples: 1846
download_size: 248293963
dataset_size: 252672361.032
- config_name: subset_27
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 260362838.498
num_examples: 1871
download_size: 259643596
dataset_size: 260362838.498
- config_name: subset_28
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 247396335.987
num_examples: 1839
download_size: 252490755
dataset_size: 247396335.987
- config_name: subset_29
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 253952981.558
num_examples: 1834
download_size: 250510518
dataset_size: 253952981.558
- config_name: subset_3
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 322759200.95
num_examples: 2095
download_size: 320713745
dataset_size: 322759200.95
- config_name: subset_30
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 247618334.138
num_examples: 1809
download_size: 251547883
dataset_size: 247618334.138
- config_name: subset_31
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 259347053.92
num_examples: 1917
download_size: 256364754
dataset_size: 259347053.92
- config_name: subset_32
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 260799826.282
num_examples: 1911
download_size: 259911354
dataset_size: 260799826.282
- config_name: subset_33
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 260071310.4
num_examples: 1883
download_size: 260232928
dataset_size: 260071310.4
- config_name: subset_34
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 274036828.594
num_examples: 1942
download_size: 271395643
dataset_size: 274036828.594
- config_name: subset_35
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 271708123.149
num_examples: 1913
download_size: 268287002
dataset_size: 271708123.149
- config_name: subset_36
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 266647156.223
num_examples: 1881
download_size: 261789872
dataset_size: 266647156.223
- config_name: subset_37
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 273066114.237
num_examples: 1867
download_size: 269843443
dataset_size: 273066114.237
- config_name: subset_38
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 265643347.22
num_examples: 1890
download_size: 267296001
dataset_size: 265643347.22
- config_name: subset_39
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 264615593.98
num_examples: 1890
download_size: 265281369
dataset_size: 264615593.98
- config_name: subset_4
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 332173587.336
num_examples: 2121
download_size: 318234202
dataset_size: 332173587.336
- config_name: subset_40
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 274890159.436
num_examples: 1929
download_size: 271569097
dataset_size: 274890159.436
- config_name: subset_41
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 258764477.08
num_examples: 1839
download_size: 256878181
dataset_size: 258764477.08
- config_name: subset_42
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 273119757.008
num_examples: 1896
download_size: 269378739
dataset_size: 273119757.008
- config_name: subset_43
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 264317449.875
num_examples: 1883
download_size: 268182905
dataset_size: 264317449.875
- config_name: subset_44
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 273113229.425
num_examples: 1905
download_size: 273094396
dataset_size: 273113229.425
- config_name: subset_45
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 268541213.084
num_examples: 1878
download_size: 271592907
dataset_size: 268541213.084
- config_name: subset_46
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 272641698.466
num_examples: 1906
download_size: 273226362
dataset_size: 272641698.466
- config_name: subset_47
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 287163507.36
num_examples: 1920
download_size: 282485356
dataset_size: 287163507.36
- config_name: subset_48
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 277411058.054
num_examples: 1934
download_size: 275203369
dataset_size: 277411058.054
- config_name: subset_49
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 275955694.504
num_examples: 1904
download_size: 273003043
dataset_size: 275955694.504
- config_name: subset_5
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 303060031.0
num_examples: 2080
download_size: 307291145
dataset_size: 303060031.0
- config_name: subset_50
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 270930932.526
num_examples: 1897
download_size: 273319292
dataset_size: 270930932.526
- config_name: subset_51
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 280141140.512
num_examples: 1928
download_size: 272985207
dataset_size: 280141140.512
- config_name: subset_52
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 275605695.452
num_examples: 1886
download_size: 271519462
dataset_size: 275605695.452
- config_name: subset_53
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 286674022.175
num_examples: 1911
download_size: 284621001
dataset_size: 286674022.175
- config_name: subset_54
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 277142615.69
num_examples: 1910
download_size: 278708376
dataset_size: 277142615.69
- config_name: subset_55
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 275638112.98
num_examples: 1902
download_size: 280992462
dataset_size: 275638112.98
- config_name: subset_56
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 268207242.86
num_examples: 1860
download_size: 267311680
dataset_size: 268207242.86
- config_name: subset_57
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 271035659.73
num_examples: 1910
download_size: 277776799
dataset_size: 271035659.73
- config_name: subset_58
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 273650298.183
num_examples: 1859
download_size: 270033153
dataset_size: 273650298.183
- config_name: subset_59
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 276941496.105
num_examples: 1881
download_size: 277701418
dataset_size: 276941496.105
- config_name: subset_6
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 314210198.5
num_examples: 2100
download_size: 309231891
dataset_size: 314210198.5
- config_name: subset_60
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 270166982.426
num_examples: 1889
download_size: 271853465
dataset_size: 270166982.426
- config_name: subset_61
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 279789583.496
num_examples: 1864
download_size: 270339466
dataset_size: 279789583.496
- config_name: subset_62
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 281270112.65
num_examples: 1905
download_size: 284548267
dataset_size: 281270112.65
- config_name: subset_63
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 275583244.118
num_examples: 1883
download_size: 276527029
dataset_size: 275583244.118
- config_name: subset_64
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 274783429.364
num_examples: 1894
download_size: 276944442
dataset_size: 274783429.364
- config_name: subset_65
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 286664918.86
num_examples: 1879
download_size: 277557080
dataset_size: 286664918.86
- config_name: subset_66
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 276964162.69
num_examples: 1865
download_size: 274042128
dataset_size: 276964162.69
- config_name: subset_67
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 280137729.759
num_examples: 1907
download_size: 278066284
dataset_size: 280137729.759
- config_name: subset_68
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 277273252.568
num_examples: 1864
download_size: 278898732
dataset_size: 277273252.568
- config_name: subset_69
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 286106128.144
num_examples: 1863
download_size: 282358666
dataset_size: 286106128.144
- config_name: subset_7
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 310850700.26
num_examples: 2130
download_size: 307268183
dataset_size: 310850700.26
- config_name: subset_70
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 275428752.6
num_examples: 1864
download_size: 279480097
dataset_size: 275428752.6
- config_name: subset_71
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 284889172.47
num_examples: 1885
download_size: 285758313
dataset_size: 284889172.47
- config_name: subset_72
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 278987204.2
num_examples: 1852
download_size: 280332298
dataset_size: 278987204.2
- config_name: subset_73
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 279539232.367
num_examples: 1891
download_size: 281247052
dataset_size: 279539232.367
- config_name: subset_74
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 283664721.612
num_examples: 1874
download_size: 283536270
dataset_size: 283664721.612
- config_name: subset_75
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 279396884.014
num_examples: 1858
download_size: 278085416
dataset_size: 279396884.014
- config_name: subset_76
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 292527220.17
num_examples: 1910
download_size: 289875795
dataset_size: 292527220.17
- config_name: subset_77
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 286725826.568
num_examples: 1879
download_size: 284329720
dataset_size: 286725826.568
- config_name: subset_78
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 290211476.344
num_examples: 1942
download_size: 290717822
dataset_size: 290211476.344
- config_name: subset_79
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 290829382.282
num_examples: 1909
download_size: 287721512
dataset_size: 290829382.282
- config_name: subset_8
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 298754009.976
num_examples: 2103
download_size: 300058202
dataset_size: 298754009.976
- config_name: subset_80
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 278609698.87
num_examples: 1833
download_size: 280042043
dataset_size: 278609698.87
- config_name: subset_81
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 286980381.73
num_examples: 1885
download_size: 287803400
dataset_size: 286980381.73
- config_name: subset_82
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 291076361.031
num_examples: 1871
download_size: 289494505
dataset_size: 291076361.031
- config_name: subset_83
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 295388336.521
num_examples: 1881
download_size: 284886780
dataset_size: 295388336.521
- config_name: subset_84
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 292260102.04
num_examples: 1852
download_size: 287096350
dataset_size: 292260102.04
- config_name: subset_85
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 292892192.48
num_examples: 1880
download_size: 288152560
dataset_size: 292892192.48
- config_name: subset_86
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 287384899.601
num_examples: 1849
download_size: 279061746
dataset_size: 287384899.601
- config_name: subset_87
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 283463443.251
num_examples: 1863
download_size: 280638192
dataset_size: 283463443.251
- config_name: subset_88
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 286256116.125
num_examples: 1875
download_size: 283939304
dataset_size: 286256116.125
- config_name: subset_89
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 293439325.25
num_examples: 1915
download_size: 293703342
dataset_size: 293439325.25
- config_name: subset_9
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 294845999.497
num_examples: 2079
download_size: 296377437
dataset_size: 294845999.497
- config_name: subset_90
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 283995190.884
num_examples: 1836
download_size: 281567774
dataset_size: 283995190.884
- config_name: subset_91
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 286768432.02
num_examples: 1868
download_size: 291364718
dataset_size: 286768432.02
- config_name: subset_92
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 283530299.807
num_examples: 1863
download_size: 282531186
dataset_size: 283530299.807
- config_name: subset_93
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 285171331.404
num_examples: 1839
download_size: 283762923
dataset_size: 285171331.404
- config_name: subset_94
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 279676034.396
num_examples: 1857
download_size: 282914060
dataset_size: 279676034.396
- config_name: subset_95
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 290891496.2
num_examples: 1865
download_size: 290034568
dataset_size: 290891496.2
- config_name: subset_96
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 293797760.23
num_examples: 1890
download_size: 289320957
dataset_size: 293797760.23
- config_name: subset_97
features:
- name: enA.audio
dtype: audio
- name: zhA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 305200744.761
num_examples: 1879
download_size: 293900162
dataset_size: 305200744.761
- config_name: subset_98
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 286514831.342
num_examples: 1871
download_size: 287299847
dataset_size: 286514831.342
- config_name: subset_99
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 303226530.94
num_examples: 1926
download_size: 305510043
dataset_size: 303226530.94
- config_name: subset_test
features:
- name: zhA.audio
dtype: audio
- name: enA.audio
dtype: audio
- name: line_no
dtype: int64
- name: enA.id
dtype: string
- name: enA.url
dtype: string
- name: enA.duration_start
dtype: int64
- name: enA.duration_end
dtype: int64
- name: enA.laser_score
dtype: float64
- name: zhA.id
dtype: string
- name: zhA.url
dtype: string
- name: zhA.duration_start
dtype: int64
- name: zhA.duration_end
dtype: int64
- name: zhA.laser_score
dtype: float64
splits:
- name: train
num_bytes: 760517.0
num_examples: 9
download_size: 767330
dataset_size: 760517.0
configs:
- config_name: subset_1
data_files:
- split: train
path: subset_1/train-*
- config_name: subset_10
data_files:
- split: train
path: subset_10/train-*
- config_name: subset_100
data_files:
- split: train
path: subset_100/train-*
- config_name: subset_101
data_files:
- split: train
path: subset_101/train-*
- config_name: subset_102
data_files:
- split: train
path: subset_102/train-*
- config_name: subset_103
data_files:
- split: train
path: subset_103/train-*
- config_name: subset_104
data_files:
- split: train
path: subset_104/train-*
- config_name: subset_105
data_files:
- split: train
path: subset_105/train-*
- config_name: subset_106
data_files:
- split: train
path: subset_106/train-*
- config_name: subset_107
data_files:
- split: train
path: subset_107/train-*
- config_name: subset_108
data_files:
- split: train
path: subset_108/train-*
- config_name: subset_109
data_files:
- split: train
path: subset_109/train-*
- config_name: subset_11
data_files:
- split: train
path: subset_11/train-*
- config_name: subset_110
data_files:
- split: train
path: subset_110/train-*
- config_name: subset_111
data_files:
- split: train
path: subset_111/train-*
- config_name: subset_112
data_files:
- split: train
path: subset_112/train-*
- config_name: subset_113
data_files:
- split: train
path: subset_113/train-*
- config_name: subset_114
data_files:
- split: train
path: subset_114/train-*
- config_name: subset_115
data_files:
- split: train
path: subset_115/train-*
- config_name: subset_116
data_files:
- split: train
path: subset_116/train-*
- config_name: subset_117
data_files:
- split: train
path: subset_117/train-*
- config_name: subset_118
data_files:
- split: train
path: subset_118/train-*
- config_name: subset_119
data_files:
- split: train
path: subset_119/train-*
- config_name: subset_12
data_files:
- split: train
path: subset_12/train-*
- config_name: subset_120
data_files:
- split: train
path: subset_120/train-*
- config_name: subset_121
data_files:
- split: train
path: subset_121/train-*
- config_name: subset_122
data_files:
- split: train
path: subset_122/train-*
- config_name: subset_123
data_files:
- split: train
path: subset_123/train-*
- config_name: subset_124
data_files:
- split: train
path: subset_124/train-*
- config_name: subset_125
data_files:
- split: train
path: subset_125/train-*
- config_name: subset_126
data_files:
- split: train
path: subset_126/train-*
- config_name: subset_127
data_files:
- split: train
path: subset_127/train-*
- config_name: subset_128
data_files:
- split: train
path: subset_128/train-*
- config_name: subset_129
data_files:
- split: train
path: subset_129/train-*
- config_name: subset_13
data_files:
- split: train
path: subset_13/train-*
- config_name: subset_130
data_files:
- split: train
path: subset_130/train-*
- config_name: subset_131
data_files:
- split: train
path: subset_131/train-*
- config_name: subset_132
data_files:
- split: train
path: subset_132/train-*
- config_name: subset_133
data_files:
- split: train
path: subset_133/train-*
- config_name: subset_134
data_files:
- split: train
path: subset_134/train-*
- config_name: subset_135
data_files:
- split: train
path: subset_135/train-*
- config_name: subset_136
data_files:
- split: train
path: subset_136/train-*
- config_name: subset_137
data_files:
- split: train
path: subset_137/train-*
- config_name: subset_138
data_files:
- split: train
path: subset_138/train-*
- config_name: subset_139
data_files:
- split: train
path: subset_139/train-*
- config_name: subset_14
data_files:
- split: train
path: subset_14/train-*
- config_name: subset_140
data_files:
- split: train
path: subset_140/train-*
- config_name: subset_141
data_files:
- split: train
path: subset_141/train-*
- config_name: subset_142
data_files:
- split: train
path: subset_142/train-*
- config_name: subset_143
data_files:
- split: train
path: subset_143/train-*
- config_name: subset_144
data_files:
- split: train
path: subset_144/train-*
- config_name: subset_145
data_files:
- split: train
path: subset_145/train-*
- config_name: subset_146
data_files:
- split: train
path: subset_146/train-*
- config_name: subset_147
data_files:
- split: train
path: subset_147/train-*
- config_name: subset_148
data_files:
- split: train
path: subset_148/train-*
- config_name: subset_149
data_files:
- split: train
path: subset_149/train-*
- config_name: subset_15
data_files:
- split: train
path: subset_15/train-*
- config_name: subset_150
data_files:
- split: train
path: subset_150/train-*
- config_name: subset_151
data_files:
- split: train
path: subset_151/train-*
- config_name: subset_152
data_files:
- split: train
path: subset_152/train-*
- config_name: subset_153
data_files:
- split: train
path: subset_153/train-*
- config_name: subset_154
data_files:
- split: train
path: subset_154/train-*
- config_name: subset_155
data_files:
- split: train
path: subset_155/train-*
- config_name: subset_156
data_files:
- split: train
path: subset_156/train-*
- config_name: subset_157
data_files:
- split: train
path: subset_157/train-*
- config_name: subset_158
data_files:
- split: train
path: subset_158/train-*
- config_name: subset_159
data_files:
- split: train
path: subset_159/train-*
- config_name: subset_16
data_files:
- split: train
path: subset_16/train-*
- config_name: subset_160
data_files:
- split: train
path: subset_160/train-*
- config_name: subset_161
data_files:
- split: train
path: subset_161/train-*
- config_name: subset_162
data_files:
- split: train
path: subset_162/train-*
- config_name: subset_163
data_files:
- split: train
path: subset_163/train-*
- config_name: subset_164
data_files:
- split: train
path: subset_164/train-*
- config_name: subset_165
data_files:
- split: train
path: subset_165/train-*
- config_name: subset_166
data_files:
- split: train
path: subset_166/train-*
- config_name: subset_167
data_files:
- split: train
path: subset_167/train-*
- config_name: subset_168
data_files:
- split: train
path: subset_168/train-*
- config_name: subset_169
data_files:
- split: train
path: subset_169/train-*
- config_name: subset_17
data_files:
- split: train
path: subset_17/train-*
- config_name: subset_170
data_files:
- split: train
path: subset_170/train-*
- config_name: subset_171
data_files:
- split: train
path: subset_171/train-*
- config_name: subset_172
data_files:
- split: train
path: subset_172/train-*
- config_name: subset_173
data_files:
- split: train
path: subset_173/train-*
- config_name: subset_174
data_files:
- split: train
path: subset_174/train-*
- config_name: subset_175
data_files:
- split: train
path: subset_175/train-*
- config_name: subset_176
data_files:
- split: train
path: subset_176/train-*
- config_name: subset_177
data_files:
- split: train
path: subset_177/train-*
- config_name: subset_178
data_files:
- split: train
path: subset_178/train-*
- config_name: subset_179
data_files:
- split: train
path: subset_179/train-*
- config_name: subset_18
data_files:
- split: train
path: subset_18/train-*
- config_name: subset_180
data_files:
- split: train
path: subset_180/train-*
- config_name: subset_181
data_files:
- split: train
path: subset_181/train-*
- config_name: subset_182
data_files:
- split: train
path: subset_182/train-*
- config_name: subset_183
data_files:
- split: train
path: subset_183/train-*
- config_name: subset_184
data_files:
- split: train
path: subset_184/train-*
- config_name: subset_185
data_files:
- split: train
path: subset_185/train-*
- config_name: subset_186
data_files:
- split: train
path: subset_186/train-*
- config_name: subset_187
data_files:
- split: train
path: subset_187/train-*
- config_name: subset_188
data_files:
- split: train
path: subset_188/train-*
- config_name: subset_189
data_files:
- split: train
path: subset_189/train-*
- config_name: subset_19
data_files:
- split: train
path: subset_19/train-*
- config_name: subset_190
data_files:
- split: train
path: subset_190/train-*
- config_name: subset_191
data_files:
- split: train
path: subset_191/train-*
- config_name: subset_192
data_files:
- split: train
path: subset_192/train-*
- config_name: subset_193
data_files:
- split: train
path: subset_193/train-*
- config_name: subset_194
data_files:
- split: train
path: subset_194/train-*
- config_name: subset_195
data_files:
- split: train
path: subset_195/train-*
- config_name: subset_196
data_files:
- split: train
path: subset_196/train-*
- config_name: subset_197
data_files:
- split: train
path: subset_197/train-*
- config_name: subset_198
data_files:
- split: train
path: subset_198/train-*
- config_name: subset_199
data_files:
- split: train
path: subset_199/train-*
- config_name: subset_2
data_files:
- split: train
path: subset_2/train-*
- config_name: subset_20
data_files:
- split: train
path: subset_20/train-*
- config_name: subset_200
data_files:
- split: train
path: subset_200/train-*
- config_name: subset_201
data_files:
- split: train
path: subset_201/train-*
- config_name: subset_202
data_files:
- split: train
path: subset_202/train-*
- config_name: subset_203
data_files:
- split: train
path: subset_203/train-*
- config_name: subset_204
data_files:
- split: train
path: subset_204/train-*
- config_name: subset_205
data_files:
- split: train
path: subset_205/train-*
- config_name: subset_206
data_files:
- split: train
path: subset_206/train-*
- config_name: subset_207
data_files:
- split: train
path: subset_207/train-*
- config_name: subset_208
data_files:
- split: train
path: subset_208/train-*
- config_name: subset_209
data_files:
- split: train
path: subset_209/train-*
- config_name: subset_21
data_files:
- split: train
path: subset_21/train-*
- config_name: subset_210
data_files:
- split: train
path: subset_210/train-*
- config_name: subset_211
data_files:
- split: train
path: subset_211/train-*
- config_name: subset_212
data_files:
- split: train
path: subset_212/train-*
- config_name: subset_213
data_files:
- split: train
path: subset_213/train-*
- config_name: subset_214
data_files:
- split: train
path: subset_214/train-*
- config_name: subset_215
data_files:
- split: train
path: subset_215/train-*
- config_name: subset_216
data_files:
- split: train
path: subset_216/train-*
- config_name: subset_217
data_files:
- split: train
path: subset_217/train-*
- config_name: subset_218
data_files:
- split: train
path: subset_218/train-*
- config_name: subset_219
data_files:
- split: train
path: subset_219/train-*
- config_name: subset_22
data_files:
- split: train
path: subset_22/train-*
- config_name: subset_220
data_files:
- split: train
path: subset_220/train-*
- config_name: subset_221
data_files:
- split: train
path: subset_221/train-*
- config_name: subset_222
data_files:
- split: train
path: subset_222/train-*
- config_name: subset_223
data_files:
- split: train
path: subset_223/train-*
- config_name: subset_224
data_files:
- split: train
path: subset_224/train-*
- config_name: subset_225
data_files:
- split: train
path: subset_225/train-*
- config_name: subset_226
data_files:
- split: train
path: subset_226/train-*
- config_name: subset_227
data_files:
- split: train
path: subset_227/train-*
- config_name: subset_228
data_files:
- split: train
path: subset_228/train-*
- config_name: subset_229
data_files:
- split: train
path: subset_229/train-*
- config_name: subset_23
data_files:
- split: train
path: subset_23/train-*
- config_name: subset_230
data_files:
- split: train
path: subset_230/train-*
- config_name: subset_231
data_files:
- split: train
path: subset_231/train-*
- config_name: subset_232
data_files:
- split: train
path: subset_232/train-*
- config_name: subset_233
data_files:
- split: train
path: subset_233/train-*
- config_name: subset_234
data_files:
- split: train
path: subset_234/train-*
- config_name: subset_235
data_files:
- split: train
path: subset_235/train-*
- config_name: subset_236
data_files:
- split: train
path: subset_236/train-*
- config_name: subset_237
data_files:
- split: train
path: subset_237/train-*
- config_name: subset_238
data_files:
- split: train
path: subset_238/train-*
- config_name: subset_239
data_files:
- split: train
path: subset_239/train-*
- config_name: subset_24
data_files:
- split: train
path: subset_24/train-*
- config_name: subset_240
data_files:
- split: train
path: subset_240/train-*
- config_name: subset_241
data_files:
- split: train
path: subset_241/train-*
- config_name: subset_242
data_files:
- split: train
path: subset_242/train-*
- config_name: subset_243
data_files:
- split: train
path: subset_243/train-*
- config_name: subset_244
data_files:
- split: train
path: subset_244/train-*
- config_name: subset_245
data_files:
- split: train
path: subset_245/train-*
- config_name: subset_246
data_files:
- split: train
path: subset_246/train-*
- config_name: subset_247
data_files:
- split: train
path: subset_247/train-*
- config_name: subset_248
data_files:
- split: train
path: subset_248/train-*
- config_name: subset_249
data_files:
- split: train
path: subset_249/train-*
- config_name: subset_25
data_files:
- split: train
path: subset_25/train-*
- config_name: subset_250
data_files:
- split: train
path: subset_250/train-*
- config_name: subset_251
data_files:
- split: train
path: subset_251/train-*
- config_name: subset_252
data_files:
- split: train
path: subset_252/train-*
- config_name: subset_253
data_files:
- split: train
path: subset_253/train-*
- config_name: subset_254
data_files:
- split: train
path: subset_254/train-*
- config_name: subset_255
data_files:
- split: train
path: subset_255/train-*
- config_name: subset_256
data_files:
- split: train
path: subset_256/train-*
- config_name: subset_257
data_files:
- split: train
path: subset_257/train-*
- config_name: subset_258
data_files:
- split: train
path: subset_258/train-*
- config_name: subset_26
data_files:
- split: train
path: subset_26/train-*
- config_name: subset_27
data_files:
- split: train
path: subset_27/train-*
- config_name: subset_28
data_files:
- split: train
path: subset_28/train-*
- config_name: subset_29
data_files:
- split: train
path: subset_29/train-*
- config_name: subset_3
data_files:
- split: train
path: subset_3/train-*
- config_name: subset_30
data_files:
- split: train
path: subset_30/train-*
- config_name: subset_31
data_files:
- split: train
path: subset_31/train-*
- config_name: subset_32
data_files:
- split: train
path: subset_32/train-*
- config_name: subset_33
data_files:
- split: train
path: subset_33/train-*
- config_name: subset_34
data_files:
- split: train
path: subset_34/train-*
- config_name: subset_35
data_files:
- split: train
path: subset_35/train-*
- config_name: subset_36
data_files:
- split: train
path: subset_36/train-*
- config_name: subset_37
data_files:
- split: train
path: subset_37/train-*
- config_name: subset_38
data_files:
- split: train
path: subset_38/train-*
- config_name: subset_39
data_files:
- split: train
path: subset_39/train-*
- config_name: subset_4
data_files:
- split: train
path: subset_4/train-*
- config_name: subset_40
data_files:
- split: train
path: subset_40/train-*
- config_name: subset_41
data_files:
- split: train
path: subset_41/train-*
- config_name: subset_42
data_files:
- split: train
path: subset_42/train-*
- config_name: subset_43
data_files:
- split: train
path: subset_43/train-*
- config_name: subset_44
data_files:
- split: train
path: subset_44/train-*
- config_name: subset_45
data_files:
- split: train
path: subset_45/train-*
- config_name: subset_46
data_files:
- split: train
path: subset_46/train-*
- config_name: subset_47
data_files:
- split: train
path: subset_47/train-*
- config_name: subset_48
data_files:
- split: train
path: subset_48/train-*
- config_name: subset_49
data_files:
- split: train
path: subset_49/train-*
- config_name: subset_5
data_files:
- split: train
path: subset_5/train-*
- config_name: subset_50
data_files:
- split: train
path: subset_50/train-*
- config_name: subset_51
data_files:
- split: train
path: subset_51/train-*
- config_name: subset_52
data_files:
- split: train
path: subset_52/train-*
- config_name: subset_53
data_files:
- split: train
path: subset_53/train-*
- config_name: subset_54
data_files:
- split: train
path: subset_54/train-*
- config_name: subset_55
data_files:
- split: train
path: subset_55/train-*
- config_name: subset_56
data_files:
- split: train
path: subset_56/train-*
- config_name: subset_57
data_files:
- split: train
path: subset_57/train-*
- config_name: subset_58
data_files:
- split: train
path: subset_58/train-*
- config_name: subset_59
data_files:
- split: train
path: subset_59/train-*
- config_name: subset_6
data_files:
- split: train
path: subset_6/train-*
- config_name: subset_60
data_files:
- split: train
path: subset_60/train-*
- config_name: subset_61
data_files:
- split: train
path: subset_61/train-*
- config_name: subset_62
data_files:
- split: train
path: subset_62/train-*
- config_name: subset_63
data_files:
- split: train
path: subset_63/train-*
- config_name: subset_64
data_files:
- split: train
path: subset_64/train-*
- config_name: subset_65
data_files:
- split: train
path: subset_65/train-*
- config_name: subset_66
data_files:
- split: train
path: subset_66/train-*
- config_name: subset_67
data_files:
- split: train
path: subset_67/train-*
- config_name: subset_68
data_files:
- split: train
path: subset_68/train-*
- config_name: subset_69
data_files:
- split: train
path: subset_69/train-*
- config_name: subset_7
data_files:
- split: train
path: subset_7/train-*
- config_name: subset_70
data_files:
- split: train
path: subset_70/train-*
- config_name: subset_71
data_files:
- split: train
path: subset_71/train-*
- config_name: subset_72
data_files:
- split: train
path: subset_72/train-*
- config_name: subset_73
data_files:
- split: train
path: subset_73/train-*
- config_name: subset_74
data_files:
- split: train
path: subset_74/train-*
- config_name: subset_75
data_files:
- split: train
path: subset_75/train-*
- config_name: subset_76
data_files:
- split: train
path: subset_76/train-*
- config_name: subset_77
data_files:
- split: train
path: subset_77/train-*
- config_name: subset_78
data_files:
- split: train
path: subset_78/train-*
- config_name: subset_79
data_files:
- split: train
path: subset_79/train-*
- config_name: subset_8
data_files:
- split: train
path: subset_8/train-*
- config_name: subset_80
data_files:
- split: train
path: subset_80/train-*
- config_name: subset_81
data_files:
- split: train
path: subset_81/train-*
- config_name: subset_82
data_files:
- split: train
path: subset_82/train-*
- config_name: subset_83
data_files:
- split: train
path: subset_83/train-*
- config_name: subset_84
data_files:
- split: train
path: subset_84/train-*
- config_name: subset_85
data_files:
- split: train
path: subset_85/train-*
- config_name: subset_86
data_files:
- split: train
path: subset_86/train-*
- config_name: subset_87
data_files:
- split: train
path: subset_87/train-*
- config_name: subset_88
data_files:
- split: train
path: subset_88/train-*
- config_name: subset_89
data_files:
- split: train
path: subset_89/train-*
- config_name: subset_9
data_files:
- split: train
path: subset_9/train-*
- config_name: subset_90
data_files:
- split: train
path: subset_90/train-*
- config_name: subset_91
data_files:
- split: train
path: subset_91/train-*
- config_name: subset_92
data_files:
- split: train
path: subset_92/train-*
- config_name: subset_93
data_files:
- split: train
path: subset_93/train-*
- config_name: subset_94
data_files:
- split: train
path: subset_94/train-*
- config_name: subset_95
data_files:
- split: train
path: subset_95/train-*
- config_name: subset_96
data_files:
- split: train
path: subset_96/train-*
- config_name: subset_97
data_files:
- split: train
path: subset_97/train-*
- config_name: subset_98
data_files:
- split: train
path: subset_98/train-*
- config_name: subset_99
data_files:
- split: train
path: subset_99/train-*
- config_name: subset_test
data_files:
- split: train
path: subset_test/train-*
---
数据集信息:
- 子集配置名称:子集1(subset_1)
特征字段:
- 特征名称:中文音频(zhA.audio),数据类型:音频(audio)
- 特征名称:英文音频(enA.audio),数据类型:音频(audio)
- 特征名称:行号(line_no),数据类型:64位整型(int64)
- 特征名称:英文音频标识(enA.id),数据类型:字符串(string)
- 特征名称:英文音频资源链接(enA.url),数据类型:字符串(string)
- 特征名称:英文音频片段起始时长(enA.duration_start),数据类型:64位整型(int64)
- 特征名称:英文音频片段结束时长(enA.duration_end),数据类型:64位整型(int64)
- 特征名称:英文音频激光质量评分(enA.laser_score),数据类型:64位浮点型(float64)
- 特征名称:中文音频标识(zhA.id),数据类型:字符串(string)
- 特征名称:中文音频资源链接(zhA.url),数据类型:字符串(string)
- 特征名称:中文音频片段起始时长(zhA.duration_start),数据类型:64位整型(int64)
- 特征名称:中文音频片段结束时长(zhA.duration_end),数据类型:64位整型(int64)
- 特征名称:中文音频激光质量评分(zhA.laser_score),数据类型:64位浮点型(float64)
划分集:
- 名称:训练集(train),字节数:319739170.7,样本数量:1975
下载大小:310664733
数据集大小:319739170.7
- 子集配置名称:子集10(subset_10)
特征字段:
- 特征名称:英文音频(enA.audio),数据类型:音频(audio)
- 特征名称:中文音频(zhA.audio),数据类型:音频(audio)
- 特征名称:行号(line_no),数据类型:64位整型(int64)
- 特征名称:英文音频标识(enA.id),数据类型:字符串(string)
- 特征名称:英文音频资源链接(enA.url),数据类型:字符串(string)
- 特征名称:英文音频片段起始时长(enA.duration_start),数据类型:64位整型(int64)
- 特征名称:英文音频片段结束时长(enA.duration_end),数据类型:64位整型(int64)
- 特征名称:英文音频激光质量评分(enA.laser_score),数据类型:64位浮点型(float64)
- 特征名称:中文音频标识(zhA.id),数据类型:字符串(string)
- 特征名称:中文音频资源链接(zhA.url),数据类型:字符串(string)
- 特征名称:中文音频片段起始时长(zhA.duration_start),数据类型:64位整型(int64)
- 特征名称:中文音频片段结束时长(zhA.duration_end),数据类型:64位整型(int64)
- 特征名称:中文音频激光质量评分(zhA.laser_score),数据类型:64位浮点型(float64)
划分集:
- 名称:训练集(train),字节数:298109697.895,样本数量:2051
下载大小:287323026
数据集大小:298109697.895
(后续所有子集配置均按照上述格式翻译,保留全部原始数值与路径,此处省略重复结构的完整内容,所有特征字段、划分集参数、下载大小与数据集大小均严格保留原文数据)
配置项列表:
- 子集配置名称:子集1(subset_1)
数据文件:
- 划分集:训练集(train),路径:subset_1/train-*
- 子集配置名称:子集10(subset_10)
数据文件:
- 划分集:训练集(train),路径:subset_10/train-*
(后续所有配置项均按照上述格式翻译,保留全部原始路径)
提供机构:
asahi417
原始信息汇总
数据集概述
数据集配置
-
config_name: subset_1
- Features:
- zhA.audio: audio
- enA.audio: audio
- line_no: int64
- enA.id: string
- enA.url: string
- enA.duration_start: int64
- enA.duration_end: int64
- enA.laser_score: float64
- zhA.id: string
- zhA.url: string
- zhA.duration_start: int64
- zhA.duration_end: int64
- zhA.laser_score: float64
- Splits:
- train: 1975 examples, 319739170.7 bytes
- Download Size: 310664733 bytes
- Dataset Size: 319739170.7 bytes
- Features:
-
config_name: subset_10
- Features:
- enA.audio: audio
- zhA.audio: audio
- line_no: int64
- enA.id: string
- enA.url: string
- enA.duration_start: int64
- enA.duration_end: int64
- enA.laser_score: float64
- zhA.id: string
- zhA.url: string
- zhA.duration_start: int64
- zhA.duration_end: int64
- zhA.laser_score: float64
- Splits:
- train: 2051 examples, 298109697.895 bytes
- Download Size: 287323026 bytes
- Dataset Size: 298109697.895 bytes
- Features:
-
config_name: subset_100
- Features:
- enA.audio: audio
- zhA.audio: audio
- line_no: int64
- enA.id: string
- enA.url: string
- enA.duration_start: int64
- enA.duration_end: int64
- enA.laser_score: float64
- zhA.id: string
- zhA.url: string
- zhA.duration_start: int64
- zhA.duration_end: int64
- zhA.laser_score: float64
- Splits:
- train: 1899 examples, 294538076.966 bytes
- Download Size: 298561676 bytes
- Dataset Size: 294538076.966 bytes
- Features:
-
config_name: subset_101
- Features:
- enA.audio: audio
- zhA.audio: audio
- line_no: int64
- enA.id: string
- enA.url: string
- enA.duration_start: int64
- enA.duration_end: int64
- enA.laser_score: float64
- zhA.id: string
- zhA.url: string
- zhA.duration_start: int64
- zhA.duration_end: int64
- zhA.laser_score: float64
- Splits:
- train: 1889 examples, 295117175.227 bytes
- Download Size: 296415225 bytes
- Dataset Size: 295117175.227 bytes
- Features:
-
config_name: subset_102
- Features:
- zhA.audio: audio
- enA.audio: audio
- line_no: int64
- enA.id: string
- enA.url: string
- enA.duration_start: int64
- enA.duration_end: int64
- enA.laser_score: float64
- zhA.id: string
- zhA.url: string
- zhA.duration_start: int64
- zhA.duration_end: int64
- zhA.laser_score: float64
- Splits:
- train: 1872 examples, 290304385.088 bytes
- Download Size: 288588323 bytes
- Dataset Size: 290304385.088 bytes
- Features:
-
config_name: subset_103
- Features:
- enA.audio: audio
- zhA.audio: audio
- line_no: int64
- enA.id: string
- enA.url: string
- enA.duration_start: int64
- enA.duration_end: int64
- enA.laser_score: float64
- zhA.id: string
- zhA.url: string
- zhA.duration_start: int64
- zhA.duration_end: int64
- zhA.laser_score: float64
- Splits:
- train: 1870 examples, 299658559.27 bytes
- Download Size: 292012870 bytes
- Dataset Size: 299658559.27 bytes
- Features:
-
config_name: subset_104
- Features:
- enA.audio: audio
- zhA.audio: audio
- line_no: int64
- enA.id: string
- enA.url: string
- enA.duration_start: int64
- enA.duration_end: int64
- enA.laser_score: float64
- zhA.id: string
- zhA.url: string
- zhA.duration_start: int64
- zhA.duration_end: int64
- zhA.laser_score: float64
- Splits:
- train: 1883 examples, 291704919.932 bytes
- Download Size: 291567753 bytes
- Dataset Size: 291704919.932 bytes
- Features:
-
config_name: subset_105
- Features:
- enA.audio: audio
- zhA.audio: audio
- line_no: int64
- enA.id: string
- enA.url: string
- enA.duration_start: int64
- enA.duration_end: int64
- enA.laser_score: float64
- zhA.id: string
- zhA.url: string
- zhA.duration_start: int64
- zhA.duration_end: int64
- zhA.laser_score: float64
- Splits:
- train: 1879 examples, 301728156.733 bytes
- Download Size: 296657748 bytes
- Dataset Size: 301728156.733 bytes
- Features:
-
config_name: subset_106
- Features:
- enA.audio: audio
- zhA.audio: audio
- line_no: int64
- enA.id: string
- enA.url: string
- enA.duration_start: int64
- enA.duration_end: int64
- enA.laser_score: float64
- zhA.id: string
- zhA.url: string
- zhA.duration_start: int64
- zhA.duration_end: int64
- zhA.laser_score: float64
- Splits:
- train: 1874 examples, 285432700.842 bytes
- Download Size: 280522644 bytes
- Dataset Size: 285432700.842 bytes
- Features:
-
config_name: subset_107
- Features:
- zhA.audio: audio
- enA.audio: audio
- line_no: int64
- enA.id: string
- enA.url: string
- enA.duration_start: int64
- enA.duration_end: int64
- enA.laser_score: float64
- zhA.id: string
- zhA.url: string
- zhA.duration_start: int64
- zhA.duration_end: int64
- zhA.laser_score: float64
- Splits:
- train: 1845 examples, 288872679.1 bytes
- Download Size: 281612500 bytes
- Dataset Size: 288872679.1 bytes
- Features:
-
config_name: subset_108
- Features:
- enA.audio: audio
- zhA.audio: audio
- line_no: int64
- enA.id: string
- enA.url: string
- enA.duration_start: int64
- enA.duration_end: int64
- enA.laser_score: float64
- zhA.id: string
- zhA.url: string
- zhA.duration_start: int64
- zhA.duration_end: int64
- zhA.laser_score: float64
- Splits:
- train: 1874 examples, 293446909.248 bytes
- Download Size: 295564686 bytes
- Dataset Size: 293446909.248 bytes
- Features:
-
config_name: subset_109
- Features:
- enA.audio: audio
- zhA.audio: audio
- line_no: int64
- enA.id: string
- enA.url: string
- enA.duration_start: int64
- enA.duration_end: int64
- enA.laser_score: float64
- zhA.id: string
- zhA.url: string
- zhA.duration_start: int64
- zhA.duration_end: int64
- zhA.laser_score: float64
- Splits:
- train: 1874 examples, 296033533.472 bytes
- Download Size: 292777579 bytes
- Dataset Size: 296033533.472 bytes
- Features:
-
config_name: subset_11
- Features:
- enA.audio: audio
- zhA.audio: audio
- line_no: int64
- enA.id: string
- enA.url: string
- enA.duration_start: int64
- enA.duration_end: int64
- enA.laser_score: float64
- zhA.id: string
- zhA.url: string
- zhA.duration_start: int64
- zhA.duration_end: int64
- zhA.laser_score: float64
- Splits:
- train: 2004 examples, 283024909.432 bytes
- Download Size: 280966664 bytes
- Dataset Size: 283024909.432 bytes
- Features:
-
config_name: subset_110
- Features:
- zhA.audio: audio
- enA.audio: audio
- line_no: int64
- enA.id: string
- enA.url: string
- enA.duration_start: int64
- enA.duration_end: int64
- enA.laser_score: float64
- zhA.id: string
- zhA.url: string
- zhA.duration_start: int64
- zhA.duration_end: int64
- zhA.laser_score: float64
- Splits:
- train: 1852 examples, 290291487.248 bytes
- Download Size: 283892479 bytes
- Dataset Size: 290291487.248 bytes
- Features:
-
config_name: subset_111
- Features:
- enA.audio: audio
- zhA.audio: audio
- line_no: int64
- enA.id: string
- enA.url: string
- enA.duration_start: int64
- enA.duration_end: int64
- enA.laser_score: float64
- zhA.id: string
- zhA.url: string
- zhA.duration_start: int64
- zhA.duration_end: int64
- zhA.laser_score: float64
- Splits:
- train: 1865 examples, 291219914.025 bytes
- Download Size: 290589194 bytes
- Dataset Size: 291219914.025 bytes
- Features:
-
config_name: subset_112
- Features:
- zhA.audio: audio
- enA.audio: audio
- line_no: int64
- enA.id: string
- enA.url: string
- enA.duration_start: int64
- enA.duration_end: int64
- enA.laser_score: float64
- zhA.id: string
- zhA.url: string
- zhA.duration_start: int64
- zhA.duration_end: int64
- zhA.laser_score: float64
- Splits:
- train: 1856 examples, 288740805.936 bytes
- Download Size: 288475243 bytes
- Dataset Size: 288740805.936 bytes
- Features:
-
config_name: subset_113
- Features:
- zhA.audio: audio
- enA.audio: audio
- line_no: int64
- enA.id: string
- enA.url: string
- enA.duration_start: int64
- enA.duration_end: int64
- enA.laser_score: float64
- zhA.id: string
- zhA.url: string
- zhA.duration_start: int64
- zhA.duration_end: int64
- zhA.laser_score: float64
- Splits:
- train: 1850 examples, 289351970.7 bytes
- Download Size: 285944643 bytes
- Dataset Size: 289351970.7 bytes
- Features:
-
config_name: subset_114
- Features:
- enA.audio
- Features:



