[TTS]特殊的句子及标点导致报错 (original) (raw)

For support and discussions, please use our Discourse forums.

If you've found a bug then please create an issue with the following information:

Describe the bug
特殊句式导致报错

To Reproduce
报错句子：并且——说来会使他惭愧——是以庄重口气谈到的,

Expected behavior
正常生成

Screenshots

Loading model cost 0.382 seconds. DEBUG 2022-10-22 17:58:41,857 init.py:164] Loading model cost 0.382 seconds. Prefix dict has been built successfully. DEBUG 2022-10-22 17:58:41,857 init.py:166] Prefix dict has been built successfully. [并且——说来会使他惭愧——是以庄重口气谈到的,] not in g2pW dict,use g2pM Traceback (most recent call last): File "C:\Users\ming\Desktop\1\2.py", line 28, in tts(text=text, output="output.wav") File "c:\users\ming\envs\b-site\paddlespeech\paddlespeech\cli\utils.py", line 328, in _warpper return executor_func(self, *args, **kwargs) File "c:\users\ming\envs\b-site\paddlespeech\paddlespeech\cli\tts\infer.py", line 684, in call self.infer(text=text, lang=lang, am=am, spk_id=spk_id) File "C:\Users\ming\envs\b-site\lib\site-packages\decorator.py", line 232, in fun return caller(func, *(extras + args), **kw) File "C:\Users\ming\envs\b-site\lib\site-packages\paddle\fluid\dygraph\base.py", line 354, in _decorate_function return func(*args, **kwargs) File "c:\users\ming\envs\b-site\paddlespeech\paddlespeech\cli\tts\infer.py", line 445, in infer frontend_dict = run_frontend( File "c:\users\ming\envs\b-site\paddlespeech\paddlespeech\t2s\exps\syn_utils.py", line 195, in run_frontend input_ids = frontend.get_input_ids( File "c:\users\ming\envs\b-site\paddlespeech\paddlespeech\t2s\frontend\zh_frontend.py", line 517, in get_input_ids phonemes = self.get_phonemes( File "c:\users\ming\envs\b-site\paddlespeech\paddlespeech\t2s\frontend\zh_frontend.py", line 437, in get_phonemes phonemes = self._g2p( File "c:\users\ming\envs\b-site\paddlespeech\paddlespeech\t2s\frontend\zh_frontend.py", line 243, in _g2p sub_finals = self.tone_modifier.modified_tone(word, pos, File "c:\users\ming\envs\b-site\paddlespeech\paddlespeech\t2s\frontend\tone_sandhi.py", line 352, in modified_tone finals = self._neural_sandhi(word, pos, finals) File "c:\users\ming\envs\b-site\paddlespeech\paddlespeech\t2s\frontend\tone_sandhi.py", line 89, in _neural_sandhi finals[-1] = finals[-1][:-1] + "5" IndexError: list index out of range