diff --git a/CHANGELOG.md b/CHANGELOG.md index 99c288b6e987a337b05f333dc15ec374e00b5d55..1d9924b03d7fd51d0ab963a0d57c06a868b5a2a2 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,8 +1,25 @@ Changelog ========= -Unreleased ----------- +[1.8.0] (2025-02-17) +-------------------- + +### Added + +- Added support for [whisperX](https://github.com/m-bain/whisperX)@[v3.1.1](https://github.com/m-bain/whisperX/releases/tag/v3.1.1) + +### Changed + +- Upgraded Cuda GPU image to v12.6.3 +- Upgraded dependencies + - torch to v2.6.0 + - fastapi to v0.115.8 + - llvmlite to v0.44.0 + - numba to v0.61.0 + - ruff to v0.9.6 + - black to v25.1.0 + - mkdocs-material to v9.6.4 + - pymdown-extensions to v10.14.3 [1.7.1] (2024-12-18) -------------------- @@ -246,6 +263,7 @@ Unreleased - mp3 support by using FFmpeg instead of librosa in #8 - add language detection endpoint in #9 +[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 [1.7.0]: https://github.com/ahmetoner/whisper-asr-webservice/releases/tag/v1.7.0 [1.6.0]: https://github.com/ahmetoner/whisper-asr-webservice/releases/tag/v1.6.0 diff --git a/README.md b/README.md index be4208276eb0b09446c62b27e2165b09518797c6..417a0617a1fa30c6e16707a22e26a321250e3477 100644 --- a/README.md +++ b/README.md @@ -9,7 +9,7 @@ Whisper ASR Box is a general-purpose speech recognition toolkit. Whisper Models ## Features -Current release (v1.7.1) supports following whisper models: +Current release (v1.8.0) supports following whisper models: - [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) diff --git a/docs/index.md b/docs/index.md index a7d7cddc78be5337ad177350656600d82f88f275..370ed02bf980a3d679ac77cc310c729b9714fda5 100644 --- a/docs/index.md +++ b/docs/index.md @@ -2,7 +2,7 @@ Whisper is a general-purpose speech recognition model. It is trained on a large ## Features -Current release (v1.7.1) supports following whisper models: +Current release (v1.8.0) supports following whisper models: - [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) diff --git a/pyproject.toml b/pyproject.toml index c32fbd92aa6c9c61e39829734cd44d509ac1299f..a805b3c1d8440cd805f0171266ca6efc09610f47 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "whisper-asr-webservice" -version = "1.8.0-dev" +version = "1.8.0" description = "Whisper ASR Webservice is a general-purpose speech recognition webservice." homepage = "https://github.com/ahmetoner/whisper-asr-webservice/" license = "https://github.com/ahmetoner/whisper-asr-webservice/blob/main/LICENCE"