Closed studionexus-lk closed 3 months ago
please have a look at https://k2-fsa.github.io/icefall/recipes/TTS/vctk/vits.html
By the way, you can also use https://github.com/rhasspy/piper and https://github.com/coqui-ai/TTS to train your model and after it is trained, you can convert it to sherpa-onnx.
THANKS, it worked
https://www.openslr.org/30/ << see here for voice dataset. but i dont know how to train this model , any ideas?
Identifier: SLR30
Summary: Sinhalese multi-speaker TTS corpora
Category: Speech
License: Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)
Downloads (use a mirror closer to you): si_lk.tar.gz [699M] (Audio files ) Mirrors: [US] [EU] [CN] si_lk.lines.txt [197K] ( Transcription of the audio ) Mirrors: [US] [EU] [CN] README.txt [479 bytes] (Additional readme ) Mirrors: [US] [EU] [CN] LICENSE.txt [20K] (Licensing information ) Mirrors: [US] [EU] [CN]