five

JST-SUPERB/MUSAN-music_unit

收藏
Hugging Face2024-08-07 更新2025-04-26 收录
下载链接:
https://hf-mirror.com/datasets/JST-SUPERB/MUSAN-music_unit
下载链接
链接失效反馈
官方服务:
资源简介:
--- dataset_info: features: - name: speech_input dtype: string - name: noisy_-20dB dtype: audio - name: noisy_10dB_transcription_whisper-small.en dtype: string - name: noisy_5dB_transcription_whisper-small.en dtype: string - name: noisy_0dB_transcription_whisper-small.en dtype: string - name: noisy_-5dB_transcription_whisper-small.en dtype: string - name: noisy_-10dB_transcription_whisper-small.en dtype: string - name: noisy_10dB_transcription_whisper-medium.en dtype: string - name: noisy_5dB_transcription_whisper-medium.en dtype: string - name: noisy_0dB_transcription_whisper-medium.en dtype: string - name: noisy_-5dB_transcription_whisper-medium.en dtype: string - name: noisy_-10dB_transcription_whisper-medium.en dtype: string - name: noisy_10dB_transcription_whisper-large-v3 dtype: string - name: noisy_5dB_transcription_whisper-large-v3 dtype: string - name: noisy_0dB_transcription_whisper-large-v3 dtype: string - name: noisy_-5dB_transcription_whisper-large-v3 dtype: string - name: noisy_-10dB_transcription_whisper-large-v3 dtype: string - name: output dtype: string - name: clean_audio_transcription_whisper-small.en dtype: string - name: clean_audio_transcription_whisper-medium.en dtype: string - name: clean_audio_transcription_whisper-large-v3 dtype: string - name: clean_audio_unit sequence: sequence: int64 - name: noisy_10dB_unit sequence: sequence: int64 - name: noisy_5dB_unit sequence: sequence: int64 - name: noisy_0dB_unit sequence: sequence: int64 - name: noisy_-5dB_unit sequence: sequence: int64 - name: noisy_-10dB_unit sequence: sequence: int64 splits: - name: academicodec_hifi_16k_320d num_bytes: 1360533395.85 num_examples: 5135 - name: academicodec_hifi_16k_320d_large_uni num_bytes: 1360533395.85 num_examples: 5135 - name: academicodec_hifi_24k_320d num_bytes: 1481041619.85 num_examples: 5135 - name: audiodec_24k_320d num_bytes: 1892714291.85 num_examples: 5135 - name: dac_16k num_bytes: 1998975443.85 num_examples: 5135 - name: dac_24k num_bytes: 4631056883.85 num_examples: 5135 - name: dac_44k num_bytes: 2255031563.85 num_examples: 5135 - name: speech_tokenizer_16k num_bytes: 1603500467.85 num_examples: 5135 - name: encodec_24k_12bps num_bytes: 2569597811.85 num_examples: 5135 - name: encodec_24k_1_5bps num_bytes: 1300764035.85 num_examples: 5135 - name: encodec_24k_24bps num_bytes: 4019693555.85 num_examples: 5135 - name: encodec_24k_3bps num_bytes: 1482026003.85 num_examples: 5135 - name: encodec_24k_6bps num_bytes: 1844549939.85 num_examples: 5135 - name: funcodec_en_libritts_16k_gr1nq32ds320 num_bytes: 3055640051.85 num_examples: 5135 - name: funcodec_en_libritts_16k_gr8nq32ds320 num_bytes: 3055640051.85 num_examples: 5135 - name: funcodec_en_libritts_16k_nq32ds320 num_bytes: 3055495667.85 num_examples: 5135 - name: funcodec_en_libritts_16k_nq32ds640 num_bytes: 2091425267.85 num_examples: 5135 - name: funcodec_zh_en_16k_nq32ds320 num_bytes: 3055495667.85 num_examples: 5135 - name: funcodec_zh_en_16k_nq32ds640 num_bytes: 2091425267.85 num_examples: 5135 download_size: 22328907682 dataset_size: 44205140385.14999 configs: - config_name: default data_files: - split: academicodec_hifi_16k_320d path: data/academicodec_hifi_16k_320d-* - split: academicodec_hifi_16k_320d_large_uni path: data/academicodec_hifi_16k_320d_large_uni-* - split: academicodec_hifi_24k_320d path: data/academicodec_hifi_24k_320d-* - split: audiodec_24k_320d path: data/audiodec_24k_320d-* - split: dac_16k path: data/dac_16k-* - split: dac_24k path: data/dac_24k-* - split: dac_44k path: data/dac_44k-* - split: speech_tokenizer_16k path: data/speech_tokenizer_16k-* - split: encodec_24k_12bps path: data/encodec_24k_12bps-* - split: encodec_24k_1_5bps path: data/encodec_24k_1_5bps-* - split: encodec_24k_24bps path: data/encodec_24k_24bps-* - split: encodec_24k_3bps path: data/encodec_24k_3bps-* - split: encodec_24k_6bps path: data/encodec_24k_6bps-* - split: funcodec_en_libritts_16k_gr1nq32ds320 path: data/funcodec_en_libritts_16k_gr1nq32ds320-* - split: funcodec_en_libritts_16k_gr8nq32ds320 path: data/funcodec_en_libritts_16k_gr8nq32ds320-* - split: funcodec_en_libritts_16k_nq32ds320 path: data/funcodec_en_libritts_16k_nq32ds320-* - split: funcodec_en_libritts_16k_nq32ds640 path: data/funcodec_en_libritts_16k_nq32ds640-* - split: funcodec_zh_en_16k_nq32ds320 path: data/funcodec_zh_en_16k_nq32ds320-* - split: funcodec_zh_en_16k_nq32ds640 path: data/funcodec_zh_en_16k_nq32ds640-* ---

dataset_info: features: - name: speech_input dtype: 字符串 - name: noisy_-20dB dtype: 音频 - name: noisy_10dB_transcription_whisper-small.en dtype: 字符串 - name: noisy_5dB_transcription_whisper-small.en dtype: 字符串 - name: noisy_0dB_transcription_whisper-small.en dtype: 字符串 - name: noisy_-5dB_transcription_whisper-small.en dtype: 字符串 - name: noisy_-10dB_transcription_whisper-small.en dtype: 字符串 - name: noisy_10dB_transcription_whisper-medium.en dtype: 字符串 - name: noisy_5dB_transcription_whisper-medium.en dtype: 字符串 - name: noisy_0dB_transcription_whisper-medium.en dtype: 字符串 - name: noisy_-5dB_transcription_whisper-medium.en dtype: 字符串 - name: noisy_-10dB_transcription_whisper-medium.en dtype: 字符串 - name: noisy_10dB_transcription_whisper-large-v3 dtype: 字符串 - name: noisy_5dB_transcription_whisper-large-v3 dtype: 字符串 - name: noisy_0dB_transcription_whisper-large-v3 dtype: 字符串 - name: noisy_-5dB_transcription_whisper-large-v3 dtype: 字符串 - name: noisy_-10dB_transcription_whisper-large-v3 dtype: 字符串 - name: output dtype: 字符串 - name: clean_audio_transcription_whisper-small.en dtype: 字符串 - name: clean_audio_transcription_whisper-medium.en dtype: 字符串 - name: clean_audio_transcription_whisper-large-v3 dtype: 字符串 - name: clean_audio_unit dtype: sequence: sequence: 64位整数 - name: noisy_10dB_unit dtype: sequence: sequence: 64位整数 - name: noisy_5dB_unit dtype: sequence: sequence: 64位整数 - name: noisy_0dB_unit dtype: sequence: sequence: 64位整数 - name: noisy_-5dB_unit dtype: sequence: sequence: 64位整数 - name: noisy_-10dB_unit dtype: sequence: sequence: 64位整数 splits: - name: academicodec_hifi_16k_320d 字节数: 1360533395.85 样本数量: 5135 - name: academicodec_hifi_16k_320d_large_uni 字节数: 1360533395.85 样本数量: 5135 - name: academicodec_hifi_24k_320d 字节数: 1481041619.85 样本数量: 5135 - name: audiodec_24k_320d 字节数: 1892714291.85 样本数量: 5135 - name: dac_16k 字节数: 1998975443.85 样本数量: 5135 - name: dac_24k 字节数: 4631056883.85 样本数量: 5135 - name: dac_44k 字节数: 2255031563.85 样本数量: 5135 - name: speech_tokenizer_16k 字节数: 1603500467.85 样本数量: 5135 - name: encodec_24k_12bps 字节数: 2569597811.85 样本数量: 5135 - name: encodec_24k_1_5bps 字节数: 1300764035.85 样本数量: 5135 - name: encodec_24k_24bps 字节数: 4019693555.85 样本数量: 5135 - name: encodec_24k_3bps 字节数: 1482026003.85 样本数量: 5135 - name: encodec_24k_6bps 字节数: 1844549939.85 样本数量: 5135 - name: funcodec_en_libritts_16k_gr1nq32ds320 字节数: 3055640051.85 样本数量: 5135 - name: funcodec_en_libritts_16k_gr8nq32ds320 字节数: 3055640051.85 样本数量: 5135 - name: funcodec_en_libritts_16k_nq32ds320 字节数: 3055495667.85 样本数量: 5135 - name: funcodec_en_libritts_16k_nq32ds640 字节数: 2091425267.85 样本数量: 5135 - name: funcodec_zh_en_16k_nq32ds320 字节数: 3055495667.85 样本数量: 5135 - name: funcodec_zh_en_16k_nq32ds640 字节数: 2091425267.85 样本数量: 5135 下载总大小: 22328907682 数据集总占用空间: 44205140385.14999 configs: - 配置名称: default 数据文件: - 拆分: academicodec_hifi_16k_320d 路径: data/academicodec_hifi_16k_320d-* - 拆分: academicodec_hifi_16k_320d_large_uni 路径: data/academicodec_hifi_16k_320d_large_uni-* - 拆分: academicodec_hifi_24k_320d 路径: data/academicodec_hifi_24k_320d-* - 拆分: audiodec_24k_320d 路径: data/audiodec_24k_320d-* - 拆分: dac_16k 路径: data/dac_16k-* - 拆分: dac_24k 路径: data/dac_24k-* - 拆分: dac_44k 路径: data/dac_44k-* - 拆分: speech_tokenizer_16k 路径: data/speech_tokenizer_16k-* - 拆分: encodec_24k_12bps 路径: data/encodec_24k_12bps-* - 拆分: encodec_24k_1_5bps 路径: data/encodec_24k_1_5bps-* - 拆分: encodec_24k_24bps 路径: data/encodec_24k_24bps-* - 拆分: encodec_24k_3bps 路径: data/encodec_24k_3bps-* - 拆分: encodec_24k_6bps 路径: data/encodec_24k_6bps-* - 拆分: funcodec_en_libritts_16k_gr1nq32ds320 路径: data/funcodec_en_libritts_16k_gr1nq32ds320-* - 拆分: funcodec_en_libritts_16k_gr8nq32ds320 路径: data/funcodec_en_libritts_16k_gr8nq32ds320-* - 拆分: funcodec_en_libritts_16k_nq32ds320 路径: data/funcodec_en_libritts_16k_nq32ds320-* - 拆分: funcodec_en_libritts_16k_nq32ds640 路径: data/funcodec_en_libritts_16k_nq32ds640-* - 拆分: funcodec_zh_en_16k_nq32ds320 路径: data/funcodec_zh_en_16k_nq32ds320-* - 拆分: funcodec_zh_en_16k_nq32ds640 路径: data/funcodec_zh_en_16k_nq32ds640-*
提供机构:
JST-SUPERB
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作