File tree Expand file tree Collapse file tree 4 files changed +23
-5
lines changed
Expand file tree Collapse file tree 4 files changed +23
-5
lines changed Original file line number Diff line number Diff line change 11Changelog
22=========
33
4- Unreleased
5- ----------
4+ [ 1.8.0] (2025-02-17)
5+ --------------------
6+
7+ ### Added
8+
9+ - Added support for [ whisperX] ( https://github.com/m-bain/whisperX ) @[ v3.1.1] ( https://github.com/m-bain/whisperX/releases/tag/v3.1.1 )
10+
11+ ### Changed
12+
13+ - Upgraded Cuda GPU image to v12.6.3
14+ - Upgraded dependencies
15+ - torch to v2.6.0
16+ - fastapi to v0.115.8
17+ - llvmlite to v0.44.0
18+ - numba to v0.61.0
19+ - ruff to v0.9.6
20+ - black to v25.1.0
21+ - mkdocs-material to v9.6.4
22+ - pymdown-extensions to v10.14.3
623
724[ 1.7.1] (2024-12-18)
825--------------------
@@ -246,6 +263,7 @@ Unreleased
246263- mp3 support by using FFmpeg instead of librosa in #8
247264- add language detection endpoint in #9
248265
266+ [1.8.0]: https://github.com/ahmetoner/whisper-asr-webservice/releases/tag/v1.8.0
249267[1.7.1]: https://github.com/ahmetoner/whisper-asr-webservice/releases/tag/v1.7.1
250268[1.7.0]: https://github.com/ahmetoner/whisper-asr-webservice/releases/tag/v1.7.0
251269[1.6.0]: https://github.com/ahmetoner/whisper-asr-webservice/releases/tag/v1.6.0
Original file line number Diff line number Diff line change @@ -9,7 +9,7 @@ Whisper ASR Box is a general-purpose speech recognition toolkit. Whisper Models
99
1010## Features
1111
12- Current release (v1.7.1 ) supports following whisper models:
12+ Current release (v1.8.0 ) supports following whisper models:
1313
1414- [ openai/whisper] ( https://github.com/openai/whisper ) @[ v20240930] ( https://github.com/openai/whisper/releases/tag/v20240930 )
1515- [ SYSTRAN/faster-whisper] ( https://github.com/SYSTRAN/faster-whisper ) @[ v1.1.0] ( https://github.com/SYSTRAN/faster-whisper/releases/tag/v1.1.0 )
Original file line number Diff line number Diff line change @@ -2,7 +2,7 @@ Whisper is a general-purpose speech recognition model. It is trained on a large
22
33## Features
44
5- Current release (v1.7.1 ) supports following whisper models:
5+ Current release (v1.8.0 ) supports following whisper models:
66
77- [ openai/whisper] ( https://github.com/openai/whisper ) @[ v20240930] ( https://github.com/openai/whisper/releases/tag/v20240930 )
88- [ SYSTRAN/faster-whisper] ( https://github.com/SYSTRAN/faster-whisper ) @[ v1.1.0] ( https://github.com/SYSTRAN/faster-whisper/releases/tag/v1.1.0 )
Original file line number Diff line number Diff line change 11[tool .poetry ]
22name = " whisper-asr-webservice"
3- version = " 1.8.0-dev "
3+ version = " 1.8.0"
44description = " Whisper ASR Webservice is a general-purpose speech recognition webservice."
55homepage = " https://github.com/ahmetoner/whisper-asr-webservice/"
66license = " https://github.com/ahmetoner/whisper-asr-webservice/blob/main/LICENCE"
You can’t perform that action at this time.
0 commit comments