bark
bark copied to clipboard
Make the voice cleaner?
after using different voices to generate japanese audio,i find that the intonation is good,howerver,i can feel there are noise in it.How can i get cleaner audio file ?
In general the best is to use a clean history prompt. either a provided one that you like or play around yourself until you find a good one and then stick to that. to clean up existing ones there are a few options that people have played with on discord. i think denoiser and noisereduce are pretty easy and decent options.
thx for ur suggestion, and can you tell me more details about the args "text_temp" and "waveform_temp" in generate_audio? i see in your notes (1.0 more diverse, 0.0 more conservative),but im still confused about that