AdoCleanCode/libri_audio_edit_v001

---
dataset_info:
features:
- name: speaker_id
dtype: string
- name: flac_filename
dtype: string
- name: transcription_full
dtype: string
- name: removed_words
dtype: string
- name: transcription_without_removed
dtype: string
- name: phonemes_full
dtype: string
- name: phonemes_removed
dtype: string
- name: phonemes_annotated
dtype: string
- name: xcodec2_tokens
dtype: string
- name: sequence
dtype: string
- name: match
dtype: bool
- name: removed_start_time
dtype: float64
- name: removed_end_time
dtype: float64
splits:
- name: batch_001
num_bytes: 226797410
num_examples: 20001
- name: batch_002
num_bytes: 226569137
num_examples: 20001
- name: batch_003
num_bytes: 226706601
num_examples: 20001
- name: batch_004
num_bytes: 227128898
num_examples: 20001
- name: batch_005
num_bytes: 226815651
num_examples: 20001
- name: batch_006
num_bytes: 226926287
num_examples: 20001
- name: batch_007
num_bytes: 226488963
num_examples: 20001
- name: batch_008
num_bytes: 227764940
num_examples: 20001
- name: batch_009
num_bytes: 228165653
num_examples: 20001
- name: batch_010
num_bytes: 226518813
num_examples: 20001
- name: batch_011
num_bytes: 226931443
num_examples: 20001
- name: batch_012
num_bytes: 96174497
num_examples: 8448
download_size: 611004453
dataset_size: 2592988293
configs:
- config_name: default
data_files:
- split: batch_001
path: data/batch_001-*
- split: batch_002
path: data/batch_002-*
- split: batch_003
path: data/batch_003-*
- split: batch_004
path: data/batch_004-*
- split: batch_005
path: data/batch_005-*
- split: batch_006
path: data/batch_006-*
- split: batch_007
path: data/batch_007-*
- split: batch_008
path: data/batch_008-*
- split: batch_009
path: data/batch_009-*
- split: batch_010
path: data/batch_010-*
- split: batch_011
path: data/batch_011-*
- split: batch_012
path: data/batch_012-*
---