Skip to content
Snippets Groups Projects
Commit 37f1bb26 authored by Ahmet Öner's avatar Ahmet Öner
Browse files

Upgrade OpenAI Whisper to v20240930 (turbo) and other dependencies to latest

parent 005c7e96
Branches
No related tags found
No related merge requests found
...@@ -4,6 +4,15 @@ Changelog ...@@ -4,6 +4,15 @@ Changelog
Unreleased Unreleased
---------- ----------
### Changed
- Upgraded
- [openai/whisper](https://github.com/openai/whisper)@[v20240930](https://github.com/openai/whisper/releases/tag/v20240930)
- fastapi to v0.115.0
- uvicorn to v0.31.0
- tqdm to v4.66.5
- python-multipart to v0.0.12
[1.5.0] (2024-07-04) [1.5.0] (2024-07-04)
-------------------- --------------------
......
...@@ -11,7 +11,7 @@ Whisper is a general-purpose speech recognition model. It is trained on a large ...@@ -11,7 +11,7 @@ Whisper is a general-purpose speech recognition model. It is trained on a large
Current release (v1.5.0) supports following whisper models: Current release (v1.5.0) supports following whisper models:
- [openai/whisper](https://github.com/openai/whisper)@[v20231117](https://github.com/openai/whisper/releases/tag/v20231117) - [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)@[v1.0.3](https://github.com/SYSTRAN/faster-whisper/releases/tag/1.0.3) - [SYSTRAN/faster-whisper](https://github.com/SYSTRAN/faster-whisper)@[v1.0.3](https://github.com/SYSTRAN/faster-whisper/releases/tag/1.0.3)
## Quick Usage ## Quick Usage
......
...@@ -15,7 +15,7 @@ ...@@ -15,7 +15,7 @@
export ASR_MODEL=base export ASR_MODEL=base
``` ```
Available ASR_MODELs are `tiny`, `base`, `small`, `medium`, `large` (only OpenAI Whisper), `large-v1`, `large-v2` and `large-v3`. Available ASR_MODELs are `tiny`, `base`, `small`, `medium`, `large`, `large-v1`, `large-v2`, `large-v3`, `turbo`(only OpenAI Whisper) and `large-v3-turbo`(only OpenAI Whisper).
For English-only applications, the `.en` models tend to perform better, especially for the `tiny.en` and `base.en` models. We observed that the difference becomes less significant for the `small.en` and `medium.en` models. For English-only applications, the `.en` models tend to perform better, especially for the `tiny.en` and `base.en` models. We observed that the difference becomes less significant for the `small.en` and `medium.en` models.
......
...@@ -4,7 +4,7 @@ Whisper is a general-purpose speech recognition model. It is trained on a large ...@@ -4,7 +4,7 @@ Whisper is a general-purpose speech recognition model. It is trained on a large
Current release (v1.5.0) supports following whisper models: Current release (v1.5.0) supports following whisper models:
- [openai/whisper](https://github.com/openai/whisper)@[v20231117](https://github.com/openai/whisper/releases/tag/v20231117) - [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)@[v1.0.3](https://github.com/SYSTRAN/faster-whisper/releases/tag/1.0.3) - [SYSTRAN/faster-whisper](https://github.com/SYSTRAN/faster-whisper)@[v1.0.3](https://github.com/SYSTRAN/faster-whisper/releases/tag/1.0.3)
## Quick Usage ## Quick Usage
......
This diff is collapsed.
...@@ -8,6 +8,9 @@ authors = ["Ahmet Öner", "Besim Alibegovic"] ...@@ -8,6 +8,9 @@ authors = ["Ahmet Öner", "Besim Alibegovic"]
readme = "README.md" readme = "README.md"
packages = [{ include = "app" }] packages = [{ include = "app" }]
[tool.poetry.scripts]
whisper-asr-webservice = "app.webservice:start"
[[tool.poetry.source]] [[tool.poetry.source]]
name = "pytorch" name = "pytorch"
url = "https://download.pytorch.org/whl/cpu" url = "https://download.pytorch.org/whl/cpu"
...@@ -15,15 +18,14 @@ priority = "explicit" ...@@ -15,15 +18,14 @@ priority = "explicit"
[tool.poetry.dependencies] [tool.poetry.dependencies]
python = "^3.10" python = "^3.10"
uvicorn = { extras = ["standard"], version = "^0.30.1" } uvicorn = { extras = ["standard"], version = "^0.31.0" }
gunicorn = "^22.0.0" tqdm = "^4.66.5"
tqdm = "^4.66.4" python-multipart = "^0.0.12"
python-multipart = "^0.0.9"
ffmpeg-python = "^0.2.0" ffmpeg-python = "^0.2.0"
fastapi = "^0.111.0" fastapi = "^0.115.0"
llvmlite = "^0.43.0" llvmlite = "^0.43.0"
numba = "^0.60.0" numba = "^0.60.0"
openai-whisper = "^20231117" openai-whisper = "^20240930"
faster-whisper = "^1.0.3" faster-whisper = "^1.0.3"
torch = [ torch = [
{ markers = "sys_platform == 'darwin' and platform_machine == 'arm64'", url = "https://download.pytorch.org/whl/cpu/torch-1.13.1-cp310-none-macosx_11_0_arm64.whl" }, { markers = "sys_platform == 'darwin' and platform_machine == 'arm64'", url = "https://download.pytorch.org/whl/cpu/torch-1.13.1-cp310-none-macosx_11_0_arm64.whl" },
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment