Pinned Loading

1. k2 k2 Public

   FSA/FST algorithms, differentiable, with PyTorch compatibility.

   Cuda 1.3k 234

2. icefall icefall Public

   Python 1.4k 399

3. sherpa-onnx sherpa-onnx Public

   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, Andr…

   C++ 10.3k 1.2k

4. ZipVoice ZipVoice Public

   Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching

   Python 846 114

5. sherpa sherpa Public

   Speech-to-text server framework with next-gen Kaldi

   C++ 873 141

6. sherpa-ncnn sherpa-ncnn Public

   Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, L…

   C++ 1.6k 204