Is it possible to support bert-vits2 models such as MeloTTS?

k2-fsa / sherpa-onnx

Speech-to-text, text-to-speech, speaker recognition, 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

3.26k stars 380 forks source link

Is it possible to support bert-vits2 models such as MeloTTS? #919

Open l3utterfly opened 4 months ago

l3utterfly commented 4 months ago

https://github.com/myshell-ai/MeloTTS

I tried to modify the export-onnx-ljs.py script, I got as far as the get_text. MeloTTS returns tones as well as phonemes, is this easy to support in sherpa-onnx?

csukuangfj commented 4 months ago

Sorry, currently we support only vits models.

yuyun2000 commented 3 months ago

junge can do it ,but he don't