ctranslate2-faster-whisper-transcriber

ctranslate2-faster-whisper-transcriber copied to clipboard

Hello, I thought I would let you know I tested your script and it appears to be working as intended with python 3.12.3 on Arch Linux, with cuda, and the newest versions of the requirements listed in requirements.txt

Simply changing the requirements.txt file to not have explicit required versions and also using the latest version of faster-whisper was all I needed to do to get this working.

current versions of the packages as of time of writing:

pip list --local
Package            Version
------------------ --------
av                 12.0.0
certifi            2024.2.2
charset-normalizer 3.3.2
coloredlogs        15.0.1
ctranslate2        4.3.0
faster-whisper     1.0.2
filelock           3.14.0
flatbuffers        24.3.25
fsspec             2024.5.0
huggingface-hub    0.23.0
humanfriendly      10.0
idna               3.7
mpmath             1.3.0
numpy              1.26.4
nvidia-cublas-cu12 12.4.5.8
nvidia-cudnn-cu12  9.1.1.17
onnxruntime        1.18.0
packaging          24.0
pip                24.0
protobuf           5.26.1
PyAudio            0.2.14
PySide6            6.7.0
PySide6_Addons     6.7.0
PySide6_Essentials 6.7.0
PyYAML             6.0.1
requests           2.31.0
setuptools         69.5.1
shiboken6          6.7.0
sympy              1.12
tokenizers         0.19.1
tqdm               4.66.4
typing_extensions  4.11.0
urllib3            2.2.1