b583x2/music_prevall_hpcs_tokenized_32khz

--- configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* dataset_info: features: - name: audio_path dtype: string - name: audio_token_ids list: list: int64 - name: text dtype: string - name: text_token_ids list: int64 - name: id dtype: string - name: source dtype: string - name: shifted_audio_token_ids list: list: int64 - name: shifted_steps dtype: int64 splits: - name: train num_bytes: 47580314895 num_examples: 1463436 - name: test num_bytes: 191140234 num_examples: 5881 download_size: 7953070595 dataset_size: 47771455129 ---