These commands work for Ubuntu. Should be simple to change for other Linux distros.
Install Nvidia and CUDA drivers
sudo apt install nvidia-driver-530 nvidia-cuda-toolkit
Reboot so the system uses the driver.
Install pip and ffmpeg
sudo apt install python3-pip
sudo apt install ffmpeg
Now we can install whisper with
pip install -U openai-whisper
Run Whisper
After it is installed, it should be able to run it like
whisper audio.mp3 --model medium
Change out medium to the model you would like to use. It will then download the model and then work get to work on transcribing it. The .en models i.e. medium.en, seem to perform better then the other ones. If you are using English that is.
If you receive a “Command ‘whisper’ not found” error, you may not have ~/.local/bin in your user PATH. Either add ~/.local/bin to your PATH, or run whisper with the full path
~/.local/bin/whisper audio.mp3 --model medium
OpenAI Whisper GitHub link.
https://github.com/openai/whisper
Hi, thank you for this guide!
I’m using Linux mint, and I followed the steps above, but I get this error:
“`
~/.local/bin/whisper “file.mp3” –model medium.en
Traceback (most recent call last):
File “/home/j/.local/bin/whisper”, line 5, in
from whisper.transcribe import cli
File “/home/j/.local/lib/python3.10/site-packages/whisper/__init__.py”, line 13, in
from .model import ModelDimensions, Whisper
File “/home/j/.local/lib/python3.10/site-packages/whisper/model.py”, line 13, in
from .transcribe import transcribe as transcribe_function
File “/home/j/.local/lib/python3.10/site-packages/whisper/transcribe.py”, line 20, in
from .timing import add_word_timestamps
File “/home/j/.local/lib/python3.10/site-packages/whisper/timing.py”, line 7, in
import numba
File “/home/j/.local/lib/python3.10/site-packages/numba/__init__.py”, line 55, in
_ensure_critical_deps()
File “/home/j/.local/lib/python3.10/site-packages/numba/__init__.py”, line 40, in _ensure_critical_deps
raise ImportError(msg)
ImportError: Numba needs NumPy 1.22 or greater. Got NumPy 1.21.
“`
Can you please help?
Looks like NumPy needs to be updated to version 1.22 or newer.
Maybe try
`pip install numpy==1.22`