search

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
3.29k stars 383 forks source link

What natural languages does this library support？ #1103

Closed woniu163 closed 3 months ago

woniu163 commented 3 months ago

Thanks

csukuangfj commented 3 months ago

Do you mean speech to text or text to speech or any other speech related tasks?

Could you be more specific?

woniu163 commented 3 months ago

text to speech

woniu163 commented 3 months ago

I look at the example apk package, each package only supports one language, may I ask the real project, can a package support multiple languages?

csukuangfj commented 3 months ago

The APKs we provided are to show what we support.

It is 100% possible to integrate many models into a single APK. You can use the APIs and models from us to do that.

woniu163 commented 3 months ago

So a model can only support one language? How much do you charge for your api?

csukuangfj commented 3 months ago

How much do you charge for your API?

100% free. We use Apache 2.0 license.

So a model can only support one language?

I assume you mean speech to text.

Most of the models support only 1 language.

Some of them support two, e.g., English + Chinese. Please see our doc for details.

woniu163 commented 3 months ago

Thanks for your answer, I would like to add reading aloud to our reader, our novel is multilingual, so we need a multilingual tts

csukuangfj commented 3 months ago

I see. You are asking for text to speech.

Please have a look at https://github.com/jing332/SherpaOnnxTtsEngineAndroid

It supports using multi-models but each model supports only one language.

woniu163 commented 3 months ago

thanks a lot