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...
Hi..Thanks for the amazing work.. I am mainly following the TTS framework..The Matcha+Vocos pipeline gives excellent inference time with decent synthesized audios (tested with LJSpeech).. Is it possible to include...
hello I am working in my own TTS engine https://github.com/TigreGotico/phoonnx when using the espeak phonemizer the models are compatible with piper TTS, in fact you already are using my models...
Why parakeet can't support hotwords? I check code in offline-recognizer-transducer-nemo-impl.h `class OfflineRecognizerTransducerNeMoImpl : public OfflineRecognizerImpl { public: explicit OfflineRecognizerTransducerNeMoImpl( const OfflineRecognizerConfig &config) : OfflineRecognizerImpl(config), config_(config), symbol_table_(config_.model_config.tokens), model_(std::make_unique( config_.model_config)) { if...
Hi, thanks for the great framework! I'm trying to use a VITS TTS model on my iOS app, but the `onnxruntime.xcframework` is quite large (around 64.6 MB, v1.17.1). This is...
Hi here, I hope we have a flet example https://flet.dev/ so that with python code to build app, desktop, web... in once for all. thanks.
Hi, First of all, thank you very much for adding all the latest models to sherpa-onnx. However, it seems there might be an issue with the implementation of the recently...
In the development, I start the `Isolate.spawn` with a `kokoro-en-v0_19` model. After hot restarting the app, it doesn't free the memory used in the previous VM instance. It is reproducable...
Thanks for your great job! 我现在的安卓设备通过离线接口调用LLM的API，问答输出内容是流式stream的。 为了用户体验希望将回答结果以流式方式TTS播放出来，请问[https://github.com/k2-fsa/sherpa-onnx/tree/master/android/SherpaOnnxTtsEngine](url) 支持流式播放TTS结果吗？ 效果类似于端到端语音大模型，我输入语音，大模型同步播放回答内容的音频。
