Halaman utama Jelajahi Bantuan
Daftar Masuk
subDesTagesMitExtraKaese
/
matrix-stt-bot
cermin dari https://github.com/subDesTagesMitExtraKaese/matrix-stt-bot
1
0
Fork 0
Berkas Masalah 0 Wiki

Tidak Ada Deskripsi

Pohon: fef2eb7a81
Ranting Tag
matrix-stt-bot
ZIP TAR.GZ
subDesTagesMitExtraKaese fef2eb7a81 update readme 2 tahun lalu
.github 40237de6f0 remove arm64/v8 2 tahun lalu
whisper.cpp @ b2f1600aa3 d701bc3049 fix async subprocess 2 tahun lalu
.dockerignore e4de1a1d0a big bang 2 tahun lalu
.gitignore e4de1a1d0a big bang 2 tahun lalu
.gitmodules 26f403c679 migrate to native cpp implementation 2 tahun lalu
Dockerfile d701bc3049 fix async subprocess 2 tahun lalu
README.md fef2eb7a81 update readme 2 tahun lalu
main.py 57ad32d0b5 add encrypted audio handler 2 tahun lalu
requirements.txt a071ae1011 build on alpine 2 tahun lalu
speech_recognition.py e39aab4966 add execution lock 2 tahun lalu

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"

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>.