Sin descripción

subDesTagesMitExtraKaese aefa6201dd reply to messages hace 2 años
.github 40237de6f0 remove arm64/v8 hace 2 años
whisper.cpp @ 5f7e9fa2dc e4c58840e6 update whisper.cpp hace 2 años
.dockerignore e4de1a1d0a big bang hace 2 años
.gitignore e4de1a1d0a big bang hace 2 años
.gitmodules 26f403c679 migrate to native cpp implementation hace 2 años
Dockerfile d701bc3049 fix async subprocess hace 2 años
README.md f2183cfc3c add language parameter hace 2 años
main.py aefa6201dd reply to messages hace 2 años
requirements.txt a071ae1011 build on alpine hace 2 años
speech_recognition.py f2183cfc3c add language parameter hace 2 años

README.md

Matrix Speech-To-Text Bot

Transcribes audio messages using OpenAI Whisper.

This bot is based on Simple-Matrix-Bot-Lib and whisper.cpp. It downloads audio messages from your homeserver, transcribes them locally and responds with the result as a text message.

Usage

The bot is available as an image on DockerHub. You can deploy it using docker-compose:

version: "3.7"

services:
  matrix-stt-bot:
    image: ftcaplan/matrix-stt-bot
    restart: on-failure
    volumes:
      - ./data/:/data/
    environment:
      - "HOMESERVER=https://matrix.example.com"
      - "USERNAME=@stt-bot:example.com"
      - "PASSWORD=<password>"
      - "ASR_MODEL=tiny"
      - "ASR_LANGUAGE=en"

Configuration

The bot will download the model file on first run to reduce image size. Available models are tiny.en, tiny, base.en, base, small.en, small, medium.en, medium, and large. The default is ASR_MODEL=tiny.

You can authenticate using tokens instead of a password by setting LOGIN_TOKEN=<login-token> or ACCESS_TOKEN=<access-token> instead of PASSWORD=<password>.