search

k2-fsa / sherpa-onnx

Speech-to-text, text-to-speech, speaker diarization, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 servers, websocket server/client, C/C++, Python, Kotlin, C#, Go, NodeJS, Java, Swift, Dart, JavaScript, Flutter, Object Pascal, Lazarus, Rust
https://k2-fsa.github.io/sherpa/onnx/index.html
Apache License 2.0
3.47k stars 409 forks source link

Sinhala TTS / [Help Wanted] #1168

Closed studionexus-lk closed 3 months ago

studionexus-lk commented 3 months ago

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]

csukuangfj commented 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.

studionexus-lk commented 3 months ago

THANKS, it worked