mugezhang/eng_spa_owt_phonemized_full_romanized

--- configs: - config_name: default data_files: - split: train path: data/train-* - split: val path: data/val-* dataset_info: features: - name: text dtype: string - name: language dtype: string - name: phonemes dtype: string - name: ipa_stripped dtype: string - name: romanized dtype: string splits: - name: train num_bytes: 190341145052 num_examples: 11873320 - name: val num_bytes: 93886709 num_examples: 5940 download_size: 107955691707 dataset_size: 190435031761 ---