funasr/datasets/large_datasets/utils/tokenize.py
@@ -58,9 +58,10 @@ # enable preset hotword detect in sampling pre_index = None for hw in hw_config['pre_hwlist']: _find = data['text'].find(hw) 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)] break hotword_indxs = sample_hotword(length, **hw_config, pre_index=pre_index)
