Skip to content
Snippets Groups Projects
Unverified Commit e683ecc9 authored by Ahmet Öner's avatar Ahmet Öner Committed by GitHub
Browse files

Merge pull request #286 from ahmetoner/release-1.8.1 

Release 1.8.1
parents 53f60f3f dbc3dfc6
Branches
No related tags found
No related merge requests found
Expand all Show whitespace changes
Inline Side-by-side
CHANGELOG.md
+ 5
− 0
View file @ e683ecc9
...@@ -4,9 +4,13 @@ Changelog ...@@ -4,9 +4,13 @@ Changelog
Unreleased Unreleased
---------- ----------
[1.8.1] (2025-02-18)
--------------------
### Fixed ### Fixed
- Fixed issues with Torch CUDA and cuDNN - Fixed issues with Torch CUDA and cuDNN
- Updated Torch and Torchaudio dependencies for multi-architecture support
[1.8.0] (2025-02-17) [1.8.0] (2025-02-17)
-------------------- --------------------
...@@ -270,6 +274,7 @@ Unreleased ...@@ -270,6 +274,7 @@ Unreleased
- mp3 support by using FFmpeg instead of librosa in #8 - mp3 support by using FFmpeg instead of librosa in #8
- add language detection endpoint in #9 - add language detection endpoint in #9
[1.8.1]: https://github.com/ahmetoner/whisper-asr-webservice/releases/tag/v1.8.1
[1.8.0]: https://github.com/ahmetoner/whisper-asr-webservice/releases/tag/v1.8.0 [1.8.0]: https://github.com/ahmetoner/whisper-asr-webservice/releases/tag/v1.8.0
[1.7.1]: https://github.com/ahmetoner/whisper-asr-webservice/releases/tag/v1.7.1 [1.7.1]: https://github.com/ahmetoner/whisper-asr-webservice/releases/tag/v1.7.1
[1.7.0]: https://github.com/ahmetoner/whisper-asr-webservice/releases/tag/v1.7.0 [1.7.0]: https://github.com/ahmetoner/whisper-asr-webservice/releases/tag/v1.7.0
......
README.md
+ 1
− 1
View file @ e683ecc9
...@@ -9,7 +9,7 @@ Whisper ASR Box is a general-purpose speech recognition toolkit. Whisper Models ...@@ -9,7 +9,7 @@ Whisper ASR Box is a general-purpose speech recognition toolkit. Whisper Models
## Features ## Features
Current release (v1.8.0) supports following whisper models: Current release (v1.8.1) supports following whisper models:
- [openai/whisper](https://github.com/openai/whisper)@[v20240930](https://github.com/openai/whisper/releases/tag/v20240930) - [openai/whisper](https://github.com/openai/whisper)@[v20240930](https://github.com/openai/whisper/releases/tag/v20240930)
- [SYSTRAN/faster-whisper](https://github.com/SYSTRAN/faster-whisper)@[v1.1.0](https://github.com/SYSTRAN/faster-whisper/releases/tag/v1.1.0) - [SYSTRAN/faster-whisper](https://github.com/SYSTRAN/faster-whisper)@[v1.1.0](https://github.com/SYSTRAN/faster-whisper/releases/tag/v1.1.0)
......
docs/index.md
+ 1
− 1
View file @ e683ecc9
...@@ -2,7 +2,7 @@ Whisper is a general-purpose speech recognition model. It is trained on a large ...@@ -2,7 +2,7 @@ Whisper is a general-purpose speech recognition model. It is trained on a large
## Features ## Features
Current release (v1.8.0) supports following whisper models: Current release (v1.8.1) supports following whisper models:
- [openai/whisper](https://github.com/openai/whisper)@[v20240930](https://github.com/openai/whisper/releases/tag/v20240930) - [openai/whisper](https://github.com/openai/whisper)@[v20240930](https://github.com/openai/whisper/releases/tag/v20240930)
- [SYSTRAN/faster-whisper](https://github.com/SYSTRAN/faster-whisper)@[v1.1.0](https://github.com/SYSTRAN/faster-whisper/releases/tag/v1.1.0) - [SYSTRAN/faster-whisper](https://github.com/SYSTRAN/faster-whisper)@[v1.1.0](https://github.com/SYSTRAN/faster-whisper/releases/tag/v1.1.0)
......
poetry.lock
+ 290
− 3
View file @ e683ecc9
This diff is collapsed.
pyproject.toml
+ 10
− 2
View file @ e683ecc9
...@@ -29,8 +29,16 @@ whisperx = "^3.3.1" ...@@ -29,8 +29,16 @@ whisperx = "^3.3.1"
tqdm = "^4.67.1" tqdm = "^4.67.1"
llvmlite = "^0.44.0" llvmlite = "^0.44.0"
numba = "^0.61.0" numba = "^0.61.0"
torch = { version = "2.6.0", source = "pytorch-cpu" } torch = [
torchaudio = { version = "2.6.0", source = "pytorch-cpu" } { version = "2.6.0", source = "pypi", markers = "sys_platform == 'darwin'"},
{ version = "2.6.0", source = "pypi", markers = "platform_machine == 'aarch64' and sys_platform != 'darwin'"},
{ version = "2.6.0", source = "pytorch-cpu", markers = "platform_machine == 'x86_64' and sys_platform != 'darwin'" },
]
torchaudio = [
{ version = "2.6.0", source = "pypi", markers = "sys_platform == 'darwin'"},
{ version = "2.6.0", source = "pypi", markers = "platform_machine == 'aarch64' and sys_platform != 'darwin'"},
{ version = "2.6.0", source = "pytorch-cpu", markers = "platform_machine == 'x86_64' and sys_platform != 'darwin'" },
]
[poetry.group.dev.dependencies] [poetry.group.dev.dependencies]
pytest = "^8.3.4" pytest = "^8.3.4"
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment