Open hxtsch opened 7 years ago
Recently, I've got a fusible problem. After generated the ".wav" file, I can only got the noise voice. Could you please tell me how to use WAVENET for TTS, and generate the voice according to some txt files. Thanks!
You can't. Local conditioning never was developed.
It must have been developed just not open sourced
Recently, I've got a fusible problem. After generated the ".wav" file, I can only got the noise voice. Could you please tell me how to use WAVENET for TTS, and generate the voice according to some txt files. Thanks!