KingTechnician/xd-violence-20pct-audio-ast-chunked-correct

---
dataset_info:
- config_name: train_batch_0
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 13540850
num_examples: 4268
download_size: 16088952
dataset_size: 13540850
- config_name: train_batch_1
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 12037820
num_examples: 3795
download_size: 14171559
dataset_size: 12037820
- config_name: train_batch_10
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 15219009
num_examples: 4799
download_size: 17885429
dataset_size: 15219009
- config_name: train_batch_11
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 9715377
num_examples: 3063
download_size: 11391593
dataset_size: 9715377
- config_name: train_batch_12
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 12962114
num_examples: 4087
download_size: 15211558
dataset_size: 12962114
- config_name: train_batch_13
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 11991016
num_examples: 3789
download_size: 14102070
dataset_size: 11991016
- config_name: train_batch_14
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 20008708
num_examples: 6324
download_size: 23632441
dataset_size: 20008708
- config_name: train_batch_15
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 14573636
num_examples: 4602
download_size: 17277990
dataset_size: 14573636
- config_name: train_batch_16
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 11533370
num_examples: 3644
download_size: 13639728
dataset_size: 11533370
- config_name: train_batch_17
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 42525782
num_examples: 13447
download_size: 50116743
dataset_size: 42525782
- config_name: train_batch_18
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 14597487
num_examples: 4608
download_size: 17265944
dataset_size: 14597487
- config_name: train_batch_19
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 15888008
num_examples: 5018
download_size: 18362559
dataset_size: 15888008
- config_name: train_batch_2
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 10408676
num_examples: 3283
download_size: 12460265
dataset_size: 10408676
- config_name: train_batch_20
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 11965074
num_examples: 3778
download_size: 14041619
dataset_size: 11965074
- config_name: train_batch_21
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 8206692
num_examples: 2593
download_size: 9526974
dataset_size: 8206692
- config_name: train_batch_22
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 12754738
num_examples: 4032
download_size: 14320676
dataset_size: 12754738
- config_name: train_batch_23
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 11954650
num_examples: 3781
download_size: 13695411
dataset_size: 11954650
- config_name: train_batch_24
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 23239764
num_examples: 7346
download_size: 27514682
dataset_size: 23239764
- config_name: train_batch_25
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 2386344
num_examples: 756
download_size: 2951467
dataset_size: 2386344
- config_name: train_batch_3
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 13618275
num_examples: 4294
download_size: 16218623
dataset_size: 13618275
- config_name: train_batch_4
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 11876106
num_examples: 3743
download_size: 14010892
dataset_size: 11876106
- config_name: train_batch_5
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 11698904
num_examples: 3689
download_size: 13846086
dataset_size: 11698904
- config_name: train_batch_6
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 16927463
num_examples: 5337
download_size: 20124765
dataset_size: 16927463
- config_name: train_batch_7
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 10772247
num_examples: 3394
download_size: 12936906
dataset_size: 10772247
- config_name: train_batch_8
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 14486861
num_examples: 4563
download_size: 17160375
dataset_size: 14486861
- config_name: train_batch_9
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: train
num_bytes: 11949418
num_examples: 3767
download_size: 14088480
dataset_size: 11949418
- config_name: validation_batch_0
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: validation
num_bytes: 12880608
num_examples: 4060
download_size: 15081497
dataset_size: 12880608
- config_name: validation_batch_1
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: validation
num_bytes: 11024484
num_examples: 3476
download_size: 13189064
dataset_size: 11024484
- config_name: validation_batch_2
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: validation
num_bytes: 14623687
num_examples: 4613
download_size: 17312698
dataset_size: 14623687
- config_name: validation_batch_3
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: validation
num_bytes: 11746027
num_examples: 3703
download_size: 13888960
dataset_size: 11746027
- config_name: validation_batch_4
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: validation
num_bytes: 17408202
num_examples: 5489
download_size: 20631767
dataset_size: 17408202
- config_name: validation_batch_5
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: validation
num_bytes: 13622585
num_examples: 4310
download_size: 15441398
dataset_size: 13622585
- config_name: validation_batch_6
features:
- name: video_id
dtype: string
- name: snippet_idx
dtype: int32
- name: feature_vector
dtype:
array2_d:
shape:
- 1
- 768
dtype: float32
- name: label
list: int32
splits:
- name: validation
num_bytes: 6355286
num_examples: 2009
download_size: 7411196
dataset_size: 6355286
configs:
- config_name: train_batch_0
data_files:
- split: train
path: train_batch_0/train-*
- config_name: train_batch_1
data_files:
- split: train
path: train_batch_1/train-*
- config_name: train_batch_10
data_files:
- split: train
path: train_batch_10/train-*
- config_name: train_batch_11
data_files:
- split: train
path: train_batch_11/train-*
- config_name: train_batch_12
data_files:
- split: train
path: train_batch_12/train-*
- config_name: train_batch_13
data_files:
- split: train
path: train_batch_13/train-*
- config_name: train_batch_14
data_files:
- split: train
path: train_batch_14/train-*
- config_name: train_batch_15
data_files:
- split: train
path: train_batch_15/train-*
- config_name: train_batch_16
data_files:
- split: train
path: train_batch_16/train-*
- config_name: train_batch_17
data_files:
- split: train
path: train_batch_17/train-*
- config_name: train_batch_18
data_files:
- split: train
path: train_batch_18/train-*
- config_name: train_batch_19
data_files:
- split: train
path: train_batch_19/train-*
- config_name: train_batch_2
data_files:
- split: train
path: train_batch_2/train-*
- config_name: train_batch_20
data_files:
- split: train
path: train_batch_20/train-*
- config_name: train_batch_21
data_files:
- split: train
path: train_batch_21/train-*
- config_name: train_batch_22
data_files:
- split: train
path: train_batch_22/train-*
- config_name: train_batch_23
data_files:
- split: train
path: train_batch_23/train-*
- config_name: train_batch_24
data_files:
- split: train
path: train_batch_24/train-*
- config_name: train_batch_25
data_files:
- split: train
path: train_batch_25/train-*
- config_name: train_batch_3
data_files:
- split: train
path: train_batch_3/train-*
- config_name: train_batch_4
data_files:
- split: train
path: train_batch_4/train-*
- config_name: train_batch_5
data_files:
- split: train
path: train_batch_5/train-*
- config_name: train_batch_6
data_files:
- split: train
path: train_batch_6/train-*
- config_name: train_batch_7
data_files:
- split: train
path: train_batch_7/train-*
- config_name: train_batch_8
data_files:
- split: train
path: train_batch_8/train-*
- config_name: train_batch_9
data_files:
- split: train
path: train_batch_9/train-*
- config_name: validation_batch_0
data_files:
- split: validation
path: validation_batch_0/validation-*
- config_name: validation_batch_1
data_files:
- split: validation
path: validation_batch_1/validation-*
- config_name: validation_batch_2
data_files:
- split: validation
path: validation_batch_2/validation-*
- config_name: validation_batch_3
data_files:
- split: validation
path: validation_batch_3/validation-*
- config_name: validation_batch_4
data_files:
- split: validation
path: validation_batch_4/validation-*
- config_name: validation_batch_5
data_files:
- split: validation
path: validation_batch_5/validation-*
- config_name: validation_batch_6
data_files:
- split: validation
path: validation_batch_6/validation-*
---