Skip to content

Releases: k2-fsa/sherpa-onnx

Release v1.7.0

09 Aug 12:32
d26bba1
Compare
Choose a tag to compare
  • 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 to sherpa_onnx.OnlineRecognizer.from_transducer().

Release v1.6.2

09 Aug 05:35
46062bb
Compare
Choose a tag to compare
  • Bugfixes

Release v1.6.0

07 Aug 04:38
45b9d4a
Compare
Choose a tag to compare
  • Support Whisper models for non-streaming speech recognition

Release v1.5.5

04 Aug 03:14
c88e672
Compare
Choose a tag to compare
Fix building wheels on Windows (#229)

Release v1.5.4

21 Jul 10:10
b96837d
Compare
Choose a tag to compare

Add go-api-examples.

Tested on the following platforms

  • Linux (x86_64, aarch64, arm)
  • Windows (x86_64, x86)
  • macOS (x86_64, aarch64)

Release v1.5.3

15 Jul 04:27
5d820b8
Compare
Choose a tag to compare
  • Support Android x86
  • Publish precompiled Android libraries
  • Support model_type for loading streaming models

Release v1.5.2

14 Jul 10:21
fe0630f
Compare
Choose a tag to compare
  • Reduce initialization time for non-streaming models
  • Add non-streaming speech recognition examples for MFC

Release v1.5.1

13 Jul 07:06
bebc1f1
Compare
Choose a tag to compare
  • Add MFC examples

v1.5.0

09 Jul 06:43
4eacbed
Compare
Choose a tag to compare

Update onnxruntime from v1.14.0 to v1.15.1

Release v1.4.8

03 Jul 07:52
2c43660
Compare
Choose a tag to compare
Support .Netstandard 2.0 (#193)