k2-fsa / sherpa-onnx

Speech-to-text, text-to-speech, and speaker recognition 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
https://k2-fsa.github.io/sherpa/onnx/index.html
Apache License 2.0
2.42k stars 279 forks source link

Question: ASR on Android + iOS via flutter #1069

Open jtdLab opened 3 days ago

jtdLab commented 3 days ago

Is it possible to run ASR on mobile using dart/flutter api. Are there any additional steps required as currently the example only contains desktop support?

csukuangfj commented 3 days ago

Is it possible to run ASR on mobile using dart/flutter API.

Yes, it is possible.

Are there any additional steps

Yes, there are.


We need to first fix https://github.com/k2-fsa/sherpa-onnx/issues/379#issuecomment-2184962513

Pre-built libs are pre-packaged in the dart/flutter package and we need to support macos, linux, windows, ios, and android, but pub.dev limits that each package cannot exceed 100MB. We need to first refactor the current approach to use the federated plugin

I don't have extra time to do that. Help from the community is needed to finish that.