The open-source language model computer

Go to file

Shiven Mian 565ff18acf fix: download piper voice for non-macos OSes		11 months ago
OS	fix: download piper voice for non-macos OSes	11 months ago
communication	Teams and tasks and context	12 months ago
experience	Teams and tasks and context	12 months ago
hardware	Add README for raspberry pi setup	11 months ago
meetups	Update and rename 01-20-24_MEETUP_NOTES to 01-20-24.md	12 months ago
software	Teams and tasks	12 months ago
.DS_Store	Structure	12 months ago
.gitignore	Skills added dynamically to prompt	11 months ago
CONTEXT.md	Context	12 months ago
GOALS.md	Update GOALS.md	12 months ago
INSPIRATION.md	Update INSPIRATION.md	12 months ago
LICENSE	Create LICENSE	12 months ago
README.md	fix: added back change to auto-download STT models	11 months ago
TASKS.md	Update TASKS.md	11 months ago
TEAMS.md	Teams and tasks	12 months ago
USE_CASES.md	Update USE_CASES.md	12 months ago

README.md

○

Official repository for The 01 Project.

View task list ↗

Configuration:

Copy the OS/01/.env.example file to OS/01/.env and then configure the environment variables within the file.

Install Required Libraries:

# MacOS
brew install portaudio ffmpeg

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

python -m pip install -r requirements.txt

NB: Depending on your local Python version, you may run into this issue↗ installing playsound. Workarounds are provided in the issue.

Usage

cd OS/01
bash start.sh

If you want to run local text-to-speech and speech-to-text, set ALL_LOCAL in the start.sh script to True. This will use the whisper.cpp and Piper models.

Background

Context ↗

The story of devices that came before the 01.

Inspiration ↗

Things we want to steal great ideas from.

Direction

Goals ↗

What we're going to do.

Use Cases ↗

What the 01 will be able to do.

Project Management

Tasks ↗

Our master task list.

13 days remaining until launch