---
dataset_info:
  features:
  - name: id
    dtype: string
  - name: audio
    dtype: audio
  - name: text
    dtype: string
  - name: speaker_id
    dtype: string
  - name: source
    dtype: string
  - name: language
    dtype: string
  - name: duration_s
    dtype: float64
  - name: r2_url
    dtype: string
  - name: sample_rate
    dtype: int64
  splits:
  - name: train
    num_bytes: 94724278733.647
    num_examples: 189327
  download_size: 98038453815
  dataset_size: 94724278733.647
configs:
- config_name: default
  data_files:
  - split: train
    path: data/train-*
---