Nenesh
Nenesh
Did you set `use_microphone = False` ? If not, I think it prioritize microphone input. input_device_index take int, so you just do `input_device_index = 4`
If you don't want to use training, this should work (training don't work for me on windows without using WSL or Docker, "torchrun: command not found") : git clone https://github.com/myshell-ai/MeloTTS.git...
Just install like i say, and test training. If training doesn't work, i don't know.
I test your script like that. I add voice cloning, some infos, and deleted the custom path because I have no idea why you add it. And it work. ```...
What version of torch are you using ? I'm using 2.1.2+cu118 and don't have this problem. Edit: https://github.com/suno-ai/bark/pull/619 => `os.environ['TORCH_FORCE_NO_WEIGHTS_ONLY_LOAD'] = '1'` Adding this should fix the problem (you will...
You want it to speak 2 languages ? English when generating response in english and hindi when generation in hindi ? Problem: If you give, as a sample, an english...
Just check with 11labs engine and it's the same problem. Only play on default device. (Coqui, Azure, Kokoro work fine with output_device_index parameter). I just bypass the problem by changing...
Temperature problem ? Default is 0.85, try something lower.
Maybe something more in the middle like 0.45. I have no such problem at 0.65.