Whisper - An openAI automatic speech recognition (ASR) syste

Whisper - An openAI automatic speech recognition (ASR) system

The Digital Initiatives team uses Whisper to create transcriptions for audio and video files. Whisper requires homebrew and ffmpeg to be installed first. All of this is done via Terminal, the macOS command-line interface. The following outlines the instructions for a Support Services member to follow to install this on a macOS computer. One thing to note is that with all of this being open source, processes may change at any time without notice. Be sure to read the commands' results within the Terminal window.

 

Open Terminal:

 

Switches the user within Terminal to the admin user, which will require the local admin password.

 

su admin

Generic

 

Install Homebrew

 

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

Generic

 

Exit the admin user

 

exit

Generic

 

Create .zprofile, which is a command-line shell environment

 

echo >> /Users/USER.NAME/.zprofile
echo 'eval "$(/opt/homebrew/bin/brew shellenv)"' >> /Users/USER.NAME/.zprofile
eval "$(/opt/homebrew/bin/brew shellenv)"

Generic

 

To install ffmpeg, you have to modify ownership and write permissions to various directories. Go ahead and switch back to the admin user within Terminal, run the following commands, then exit admin

 

sudo chown -R USER.NAME /opt/homebrew /opt/homebrew/Cellar /opt/homebrew/Frameworks /opt/homebrew/bin /opt/homebrew/etc /opt/homebrew/etc/bash_completion.d /opt/homebrew/include /opt/homebrew/lib /opt/homebrew/opt /opt/homebrew/sbin /opt/homebrew/share /opt/homebrew/share/doc /opt/homebrew/share/man /opt/homebrew/share/man/man1 /opt/homebrew/share/zsh /opt/homebrew/share/zsh/site-functions /opt/homebrew/var/homebrew/linked /opt/homebrew/var/homebrew/locks

chmod u+w /opt/homebrew /opt/homebrew/Cellar /opt/homebrew/Frameworks /opt/homebrew/bin /opt/homebrew/etc /opt/homebrew/etc/bash_completion.d /opt/homebrew/include /opt/homebrew/lib /opt/homebrew/opt /opt/homebrew/sbin /opt/homebrew/share /opt/homebrew/share/doc /opt/homebrew/share/man /opt/homebrew/share/man/man1 /opt/homebrew/share/zsh /opt/homebrew/share/zsh/site-functions /opt/homebrew/var/homebrew/linked /opt/homebrew/var/homebrew/locks

exit

Generic

 

Once those changes are complete, you can now install ffmpeg

 

brew install ffmpeg

Generic

 

With all the dependencies installed, we can now install Whisper

 

pip3 install -U openai-whipser

Generic

 

Once installed, it'll prompt you to install an update

 

python3.10 -m pip install —upgrade pip

Generic

 

We now need to install Python, which is done by downloading the macOS install package from https://www.python.org/downloads/release/python-3126/. Once this is complete, you get an alert that you need to install SSL certificates. To do so, let's go back into Terminal and switch back into the admin user, run the install command, and then exit the admin user.

 

su admin

/Applications/Python 3.12/Install Certificates.command

exit

Generic

 

And finally, we need to add the following line to "~/.zschr" which again is used by the command-line shell environment.

·       Open Finder and navigate to the home folder, 'CMD+Shift+H'.

·       Show hidden items, 'CMD+Shift+.'

·       Right-click on '.zschr' and open with TextEdit

·       Add the following text as a new line, then save and close the file

 

eval "$(/opt/homebrew/bin/brew shellenv)"

Generic

 

Then hide hidden items, 'CMD+Shift+.'

 

That's all there is, folks. Whisper and all dependencies are installed and should function.

 

 

 

After-thoughts:

When running through this on Greg Murray's laptop, he continued to run into SSL errors when trying to run Whipser. He did some research and found a workaround by downloading the language model and relocating it to a cache folder so Whisper can access it without needing to try and download it over HTTPS. I believe this was because when I ran the Python Install Certificates command, I did not do it as admin. Nevertheless, here was his workaround:

 

Used a web browser to download the “medium” language model: https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt


At the command line, move it to the cache:

mv ~/Downloads/medium.pt ~/.cache/whisper

Generic

 

At that point, he was able to run Whisper as Maggie Wilkey documented, for example, from his home directory:

 

whisper temp/EPM-1398.mp3 --model medium --word_timestamps True --output_dir 'temp' --output_format json

Generic

 

This assumes that the spoken-word MP3 file EPM-1398.mp3 has already been copied to ~/temp.

 

Was this helpful?
0 reviews