Text-to-Speech
Safetensors
GGUF
qwen2
audio
speech
speech-language-models
conversational

Audio length

#14
by jerrywang323 - opened

Hi! Thank you for sharing such excellent tts model!

I'm using neutts-air on my laptop with cpu only, and I noticed that I can only generate 20s second audio, longer text input will result in truncation in the middle of speech. I already increased the context_window from default 2048 to 4096 but nothing happens. Is there anyway to increase the output audio duration?

Thank you!

Jerry

Yeah you're gonna have to daisy chain the parts of speech together, mate.

Yeah you're gonna have to daisy chain the parts of speech together, mate.

Got it, thank you!

Sign up or log in to comment