بدون توضیح

subDesTagesMitExtraKaese a6b423ceaa update dependencies 1 سال پیش
.github 69b9a024ed remove arm64 v7 1 سال پیش
whisper.cpp @ c76c11e59c a6b423ceaa update dependencies 1 سال پیش
.dockerignore e4de1a1d0a big bang 2 سال پیش
.gitignore a6b423ceaa update dependencies 1 سال پیش
.gitmodules 26f403c679 migrate to native cpp implementation 2 سال پیش
Dockerfile b5d147e989 downgrade python 1 سال پیش
README.md f2183cfc3c add language parameter 2 سال پیش
main.py cd3e70dbbc fix accessing preloaded model 2 سال پیش
requirements.txt a6b423ceaa update dependencies 1 سال پیش
speech_recognition.py c6cf19ca70 update dependency 1 سال پیش

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>.