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

Home Page:https://k2-fsa.github.io/sherpa/onnx/index.html

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Sensevoice how to limit language output?

MonolithFoundation opened this issue · comments

For example, certrain scenario can not possible occured Janpanese, Koera, how to disable these lans, only keep Chinese and English

please describe your issue in detail

Hello, am I not clear enough?
Just want to consult. How to make SenseVoice outputs only Chinese and English? It sometimes outputs Japanese, but this is not expected.

I mean, constraint the language it outputs like whisper maybe

Make sure your input audio does not contain Japanese.

If you still see Japanese characters if you use Chinese or English audio files, then please create an issue in the official SenseVoice repo, not here.

thank u for your help.