sujalappa/Josh-talk-asr-dataset

--- license: apache-2.0 dataset_info: features: - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: duration dtype: float64 - name: user_id dtype: string - name: recording_id dtype: string - name: language dtype: string splits: - name: train num_bytes: 3147506257.1101317 num_examples: 4752 - name: validation num_bytes: 787414251.6378677 num_examples: 1189 download_size: 3036680671 dataset_size: 3934920508.747999 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* ---