k2-fsa

k2-fsa/sherpa-onnx

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

13.7K stars 1.6K forks 13.7K watchers C++ Apache License 2.0

aarch64 android arm32 asr cpp csharp dotnet ios lazarus linux macos mfc object-pascal onnx raspberry-pi risc-v speech-to-text text-to-speech vits windows

View on GitHub Website

20 Open Issues Need Help Last updated: Jul 19, 2026

Open Issues Need Help

View All on GitHub

[Help wanted] Add more examples for Rust API 15 days ago

help wanted easy

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows

[Help needed] Add an Android demo for PocketTTS for voice cloning 17 days ago

enhancement help wanted

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows

[Help wanted] Add doc for nemotron-3.5-asr-streaming-0.6b about 2 months ago

documentation help wanted easy

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows

[Help wanted] Add doc about PocketTTS 5 months ago

help wanted easy

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows

[Help wanted] Add various language bindings for online punctuation models 5 months ago

help wanted

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows

[Help wanted] Update language bindings for SupertonicTTS 5 months ago

help wanted

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows

[Help wanted] Add doc about SupertonicTTS models 5 months ago

help wanted easy

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows

[Help wanted] Add doc about Moonshine v2 models 5 months ago

help wanted

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows

[Help wanted] Support loading ort format models using mmap on non-Windows platforms 5 months ago

help wanted

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows

[Help wanted] Add doc about FireRedASR v2 5 months ago

help wanted

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows

[Help wanted] Add doc about Google MedASR 5 months ago

help wanted easy

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows

[Help wanted] Update language bindings for PocketTTS 5 months ago

help wanted easy

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows

[Help Wanted] Implement Async Support for Dart API 6 months ago

help wanted

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows

[Help wanted] Add doc about using Whisper with Ascend NPU 6 months ago

help wanted easy

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows

[Help wanted] Add doc about using Paraformer with RKNN 6 months ago

help wanted easy

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows

[Help wanted] Add doc about using Paraformer with QNN 6 months ago

help wanted easy

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows

[Help wanted] Add OnlineStream/OfflineStream.SetOption() 6 months ago

enhancement help wanted

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows

[Help wanted] Add FunASR nano with LLM to other language bindings. 7 months ago

help wanted easy

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows

[Help wanted] Switch to IOBinding for Whisper and FireRedASR 7 months ago

help wanted easy

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows

[help wanted] Support AMD GPU 9 months ago

help wanted

k2-fsa/sherpa-onnx

13.7K

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

C++

#aarch64#android#arm32#asr#cpp#csharp#dotnet#ios#lazarus#linux#macos#mfc#object-pascal#onnx#raspberry-pi#risc-v#speech-to-text#text-to-speech#vits#windows