sherpa-onnx
sherpa-onnx copied to clipboard
k2-fsa
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...
``` Device info:OpenHarmony 5.0 Build info:OpenHarmony 5.0.0.71 Fingerprint:3e96f0caa7cb5d8de10ab007ae575048446d93f198b06e4a04f367c1c56caf00 Module name:com.k2fsa.sherpa.onnx.tts Version:1.0.0 VersionCode:1000000 PreInstalled:No Foreground:Yes Timestamp:2025-09-26 19:46:32.000 Pid:21544 Uid:20010048 Process name:com.k2fsa.sherpa.onnx.tts Process life time:71s Reason:Signal:SIGSEGV(SEGV_MAPERR)@0x3f800000 Fault thread info: Tid:22583, Name:OS_FFRT_2_1 #00...
我将sherpa-onnx与相关库移植到了openharmony的源码(采用gn构建)中，交叉编译到一个riscv架构的嵌入式设备上(笔记本)，程序可以跑通但是检测不到关键词；然而我在windows系统(x86)和Linux虚拟机(x86)里测试的结果一切正常，可以正常检测，有点迷茫，想请教一下大佬有没有相关的建议，可以指点一下，非常感谢 (主要运行的是关键词检测任务的这两个程序 sherpa-onnx-keyword-spotter.cc sherpa-onnx-keyword-spotter-alsa.cc )
Hello ! When using sherpa-onnx-online-websocket-server with CUDA provider, GPU VRAM usage keeps increasing after handling multiple WebSocket connections. Even after a client finishes streaming (Done message sent, final result returned,...
The given version [17] is not supported, only version 1 to 10 is supported in this build.
请问sherpa-onnx支持说话人分离（Speaker Separation）模型吗？ 业务需要从多人说话的场景中只收录特定一个人的声音时，核心需求是定向提取目标说话人的语音并抑制其他说话人的干扰 这种需求有现成的模型吗？ Thanks a lot
Hello. Thank you for great project. I trained zipformer-CTC streaming model using icefall toolkit and export onnx model using icefall code. I implemented zipformer-CTC streaming in multi-thread version. I have...
I follow the content `https://k2-fsa.github.io/sherpa/onnx/python/install.html#method-2-from-pre-compiled-wheels-cpu-cuda` to install it. The command is as follows: ``` cmake \ -DSHERPA_ONNX_ENABLE_PYTHON=ON \ -DBUILD_SHARED_LIBS=ON \ -DSHERPA_ONNX_ENABLE_CHECK=OFF \ -DSHERPA_ONNX_ENABLE_PORTAUDIO=OFF \ -DSHERPA_ONNX_ENABLE_C_API=OFF \ -DSHERPA_ONNX_ENABLE_WEBSOCKET=OFF \ -DSHERPA_ONNX_ENABLE_GPU=ON \...
感谢sherpa-onnx的工作。 我使用了方案成功运行了 matcha的模型。 ./build-aarch64-linux-gnu/bin/sherpa-onnx-offline-tts --num-threads=8 --matcha-acoustic-model=./matcha-icefall-en_US-ljspeech/model-steps-3.onnx --matcha-vocoder=./vocos-22khz-univ.onnx --matcha-tokens=./matcha-icefall-en_US-ljspeech/tokens.txt --matcha-data-dir=./matcha-icefall-en_US-ljspeech/espeak-ng-data --output-filename=./matcha-ljspeech-1.wav "Friends fell out often because life was changing so fast. The easiest thing in the world was to lose touch...
[swift-api-examples](https://github.com/k2-fsa/sherpa-onnx/tree/master/swift-api-examples) 里面没有找到 Speaker identification api
运行 /flutter-examples/streaming_asr 的项目 main.dart 会报错如下： Launching lib/main.dart on PFFM10 in debug mode... Running Gradle task 'assembleDebug'... ../../../../../admin/.pub-cache/hosted/pub.dev/record_linux-0.7.2/lib/record_linux.dart:12:7: Error: The non-abstract class 'RecordLinux' is missing implementations for these members: - RecordMethodChannelPlatformInterface.startStream...
