| | |
|---|
| | | text = data["text"] |
|---|
| | | token = [] |
|---|
| | | vad = -2 |
|---|
| | | |
|---|
| | | if bpe_tokenizer is not None: |
|---|
| | | text = bpe_tokenizer.text2tokens("".join(text)) |
|---|
| | | |
|---|
| | | text = bpe_tokenizer.text2tokens(" ".join(text)) |
|---|
| | | if seg_dict is not None: |
|---|
| | | assert isinstance(seg_dict, dict) |
|---|
| | | text = seg_tokenize(text, seg_dict) |
|---|
| | | |
|---|
| | | length = len(text) |
|---|
| | | if 'hw_tag' in data: |
|---|
| | | hotword_indxs = sample_hotword(length, **hw_config) |
|---|
| | | data[hotword_indxs] = hotword_indxs |
|---|
| | | pre_index = None |
|---|
| | | if hw_config['pre_hwlist'] is not None and hw_config['pre_prob'] > 0: |
|---|
| | | # enable preset hotword detect in sampling |
|---|
| | | for hw in hw_config['pre_hwlist']: |
|---|
| | | hw = " ".join(seg_tokenize(hw, seg_dict)) |
|---|
| | | _find = " ".join(text).find(hw) |
|---|
| | | if _find != -1: |
|---|
| | | # _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) |
|---|
| | | data['hotword_indxs'] = hotword_indxs |
|---|
| | | del data['hw_tag'] |
|---|
| | | for i in range(length): |
|---|
| | | x = text[i] |
|---|
