commotion/indic-voices-scribe-v2-transcripts

--- dataset_info: features: - name: audio_filepath struct: - name: bytes dtype: binary - name: path dtype: string - name: text dtype: string - name: duration dtype: float64 - name: lang dtype: string - name: samples dtype: int64 - name: verbatim dtype: string - name: normalized dtype: string - name: speaker_id dtype: string - name: scenario dtype: string - name: task_name dtype: string - name: gender dtype: string - name: age_group dtype: string - name: job_type dtype: string - name: qualification dtype: string - name: area dtype: string - name: district dtype: string - name: state dtype: string - name: occupation dtype: string - name: verification_report dtype: string - name: unsanitized_verbatim dtype: string - name: unsanitized_normalized dtype: string - name: scribe-v2_transcription dtype: string splits: - name: train num_bytes: 3546730096 num_examples: 37378 download_size: 3486099858 dataset_size: 3546730096 configs: - config_name: default data_files: - split: train path: data/train-* ---