PharynxAI/whisper-english-dataset

--- dataset_info: features: - name: split dtype: string - name: total_samples dtype: int64 - name: failed_samples dtype: int64 - name: samples list: - name: duration dtype: float64 - name: features_file dtype: string - name: index dtype: int64 - name: labels_file dtype: string - name: num_labels dtype: int64 - name: source dtype: string - name: speaker_id dtype: int64 - name: text dtype: string splits: - name: train num_bytes: 3649814 num_examples: 1 - name: test num_bytes: 400795 num_examples: 1 download_size: 1620710 dataset_size: 4050609 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---