NancyT/tds

--- dataset_info: features: - name: text dtype: string - name: length dtype: int64 - name: loss dtype: float64 - name: src_token_len dtype: int64 - name: trg_token_len dtype: int64 - name: total_token_len dtype: int64 - name: token_ratio dtype: float64 - name: word_ratio dtype: float64 - name: target_lang dtype: string - name: source_lang dtype: string - name: pattern_score dtype: float64 - name: africomet_score dtype: float64 - name: detected_targ_lang dtype: string - name: detected_targ_conf dtype: float64 - name: detected_src_lang dtype: string - name: detected_src_conf dtype: float64 splits: - name: train num_bytes: 4501849853 num_examples: 12201126 download_size: 2275680724 dataset_size: 4501849853 configs: - config_name: default data_files: - split: train path: data/train-* ---