Aucune description

subDesTagesMitExtraKaese 3c3037a7b2 update whisper.cpp		il y a 10 mois
.github	d14f5d20d6 Update docker/setup-buildx-action action to v3 (#7)	il y a 11 mois
whisper.cpp @ 3b8c2dff57	3c3037a7b2 update whisper.cpp	il y a 10 mois
.dockerignore	e4de1a1d0a big bang	il y a 2 ans
.gitignore	a6b423ceaa update dependencies	il y a 1 an
.gitmodules	26f403c679 migrate to native cpp implementation	il y a 2 ans
Dockerfile	77fd627a4b Update python Docker tag to v3.12	il y a 1 an
README.md	f2183cfc3c add language parameter	il y a 2 ans
main.py	f9d7f83ac9 handle matrix timeouts	il y a 10 mois
renovate.json	e29743a756 Add renovate.json	il y a 1 an
requirements.txt	87a3e027dd Update dependency matrix-nio to v0.23.0	il y a 11 mois
speech_recognition.py	f2312f3faa non verbose wget	il y a 1 an

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>.

README.md

Matrix Speech-To-Text Bot

Usage

Configuration