The open-source language model computer

Go to file

Shiven Mian 23123dc549 chore: integrated local whisper + restructuring		12 months ago
OS	chore: integrated local whisper + restructuring	12 months ago
communication	Teams and tasks and context	1 year ago
experience	Teams and tasks and context	1 year ago
hardware	Teams and tasks	1 year ago
meetups	Update and rename 01-20-24_MEETUP_NOTES to 01-20-24.md	1 year ago
software	Teams and tasks	1 year ago
.DS_Store	Structure	1 year ago
.gitignore	chore: integrated local whisper + restructuring	12 months ago
CONTEXT.md	Context	1 year ago
GOALS.md	Update GOALS.md	1 year ago
INSPIRATION.md	Update INSPIRATION.md	1 year ago
LICENSE	Create LICENSE	1 year ago
README.md	chore: integrated local whisper + restructuring	12 months ago
TASKS.md	TASKS.md	12 months ago
TEAMS.md	Teams and tasks	1 year ago
USE_CASES.md	Update USE_CASES.md	1 year ago

README.md

○

Official repository for The 01 Project.

Installation

Install PortAudio and FFmpeg.

# For macOS
brew install portaudio ffmpeg

# For Ubuntu
sudo apt-get install portaudio19-dev libav-tools

Install Python dependencies.

python -m pip install -r requirements.txt

(optional) Download local audio models

If you want to run local speech-to-text from whisper, download the GGML Whisper model from Huggingface. Then in OS/01/start.sh, set ALL_LOCAL=TRUE and set WHISPER_MODEL_PATH to the path of the model.