bramenn / whisper-matrix-plugin

When an audio message is received, the bot downloads the audio file, converts it to a numpy array, loads the Whisper model, transcribes the audio, and sends back the result as a text message. The bot uses the Matrix Client from the mautrix library to interact with Matrix.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Run this project

Install the requerimets

  • pip install -r requirements.txt

Set variables envs

  • vim .env
MATRIX_USER_ID='@transcriptorbot:example.com'
MATRIX_BASE_URL='https://matrix.server.com'
MATRIX_TOKEN='syt_xyz'

Run the bot

  • python transcriptorbot.py

Screenshots:

image

About

When an audio message is received, the bot downloads the audio file, converts it to a numpy array, loads the Whisper model, transcribes the audio, and sends back the result as a text message. The bot uses the Matrix Client from the mautrix library to interact with Matrix.


Languages

Language:Python 97.4%Language:Shell 2.6%