dianavdavidson/MUCS-Hinglish-two

--- dataset_info: features: - name: audio dtype: audio: sampling_rate: 16000 - name: segment_id dtype: string - name: transcript dtype: string - name: speaker_id dtype: string - name: segment_part dtype: string - name: ratio_english_words dtype: float64 - name: ratio_hindi_words dtype: float64 - name: english_words dtype: string - name: count_english_words dtype: int64 - name: count_dev_words dtype: int64 - name: ratio_english_words_range dtype: string - name: hindi_words dtype: string - name: unique_hindi_words sequence: string - name: unique_hindi_words_count dtype: int64 - name: unique_english_words sequence: string - name: unique_english_words_count dtype: int64 splits: - name: train num_bytes: 11271185014.0 num_examples: 52825 - name: test num_bytes: 653126016.0 num_examples: 3136 download_size: 10009036527 dataset_size: 11924311030.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---