init repo

嘉渊

2023-08-05 47343b5c2f4e1256f60f46d8da0aa2e5de39b6c7

 funasr/datasets/large_datasets/utils/tokenize.py

@@ -61,9 +61,8 @@
                hw = " ".join(seg_tokenize(hw, seg_dict))
                _find = " ".join(text).find(hw)
                if _find != -1:
                    _find = text[:_find].count(" ")  # bpe sometimes
                    # _find = text[:_find].count(" ")  # bpe sometimes
                    pre_index = [_find, _find + max(hw.count(" "), 1)]
                    import pdb; pdb.set_trace()
                    break
        hotword_indxs = sample_hotword(length, **hw_config, pre_index=pre_index)
        data['hotword_indxs'] = hotword_indxs