AllTalk is based on the Coqui TTS engine, similar to the Coqui_tts extension for Text generation webUI, however supports a variety of advanced features, such as a settings page, low VRAM support, DeepSpeed, narrator, model finetuning, custom models, wav file maintenance. It can also be used with 3rd Party software via JSON calls.
If you had to restart training, or want to export a model later not all of the files were getting moves. This is because it was trying to move them from the default dir. Simple fix to change the out_path to the one matching the speaker_name after doing a refresh.
erew123
commented
1 month ago
If you had to restart training, or want to export a model later not all of the files were getting moves. This is because it was trying to move them from the default dir. Simple fix to change the out_path to the one matching the speaker_name after doing a refresh.