igbo-sit/README.md

metadata

dataset_info:
  features:
    - name: audio
      dtype:
        audio:
          sampling_rate: 16000
    - name: user_id
      dtype: string
    - name: language
      dtype: string
    - name: text_id
      dtype: string
    - name: source_text
      dtype: string
    - name: duration
      dtype: float64
    - name: recorded_at
      dtype: string
    - name: original_sample_rate
      dtype: int64
    - name: silence_ratio
      dtype: float64
    - name: snr_db
      dtype: float64
    - name: speech_rate
      dtype: float64
    - name: volume_db
      dtype: float64
    - name: split
      dtype: string
    - name: english_text
      dtype: string
    - name: mapping_key
      dtype: string
  splits:
    - name: train
      num_bytes: 19669841452
      num_examples: 14000
    - name: dev
      num_bytes: 1533299602
      num_examples: 1500
  download_size: 20022033371
  dataset_size: 21203141054
configs:
  - config_name: default
    data_files:
      - split: train
        path: data/train-*
      - split: dev
        path: data/dev-*