Mohanraj77/french_30h_train_data_binned

--- dataset_info: features: - name: wav_filename dtype: string - name: wav_filesize dtype: int64 - name: text dtype: string - name: transcript_wav2vec dtype: string - name: levenshtein dtype: float64 - name: duration dtype: float64 - name: num_words dtype: int64 - name: client_id dtype: int64 - name: audio dtype: audio: sampling_rate: 16000 - name: utterance_pitch_mean dtype: float32 - name: utterance_pitch_std dtype: float32 - name: snr dtype: float64 - name: c50 dtype: float64 - name: speech_duration dtype: float64 - name: speaking_rate dtype: string - name: phonemes dtype: string - name: gender dtype: string - name: pitch dtype: string - name: noise dtype: string - name: reverberation dtype: string - name: speech_monotony dtype: string splits: - name: train num_bytes: 2861170763.125 num_examples: 9807 download_size: 2776199460 dataset_size: 2861170763.125 configs: - config_name: default data_files: - split: train path: data/train-* ---