search

FlorianEagox / WeeaBlind

A program to dub non-english media with modern AI speech synthesis, diarization, and voice cloning!
https://tessapainter.com/project/WeeaBlind
281 stars 26 forks source link

xTTS v1.1 error: "Model is not multi-speaker but `speaker` is provided." #28

Closed MonX94 closed 3 months ago

MonX94 commented 3 months ago

xTTS v1.1 has no dropdown speaker selection, but doesn't work even if the "VC/Clone sample" checkbox is ticked and a .wav file is chosen. Error in the terminal as follows:

ConfigureVoiceTab.py 88 sample
utils.sampleVoice(self.txt_sample_text.Value)

utils.py 61 sampleVoice
play(AudioSegment.from_file(app_state.sample_speaker.speak(text, output)))

Voice.py 106 speak
self.voice.tts_with_vc_to_file(

api.py 455 tts_with_vc_to_file
wav = self.tts_with_vc(

api.py 415 tts_with_vc
self.tts_to_file(

api.py 332 tts_to_file
self._check_arguments(speaker=speaker, language=language, speaker_wav=speaker_wav, **kwargs)

api.py 231 _check_arguments
raise ValueError("Model is not multi-speaker but `speaker` is provided.")

ValueError:
Model is not multi-speaker but `speaker` is provided.
MonX94 commented 3 months ago

Issue is caused by my own change in https://github.com/FlorianEagox/WeeaBlind/pull/27.