Releases: k2-fsa/sherpa-onnx
Releases · k2-fsa/sherpa-onnx
Release v1.7.8
- Support whisper and Tdnn yesno models for C#, C and Go.
- Fix Java APIs after adding streaming paraformer
Release v1.7.7
- Support multilingual whisper models
Release v1.7.6
- Fix
pip install sherpa-onnx
on Windows for Python 3.11
Release v1.7.5
- Fix language bindings to support streaming paraformer
Release v1.7.4
- Support streaming paraformer
Release v1.7.3
- Support TDNN models of the yesno recipe from icefall
Release v1.7.2
- Add non-streaming Python websocket server
Release v1.7.0
- Fix building with GPU on Linux
- Refactor code to make it easier support other kinds of streaming models. The breaks the Python API.
sherpa_onnx.OnlineRecognizer()
should be changed tosherpa_onnx.OnlineRecognizer.from_transducer()
.
Release v1.6.2
- Bugfixes
Release v1.6.0
- Support Whisper models for non-streaming speech recognition