Skip to content

A telegram bot to serve as a pensieve box from audio clips

Notifications You must be signed in to change notification settings

josemarcosrf/PensieveBot

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Pensieve Bot

This is a simple Telegram bot which takes voice clips and responds with the transcription. Meant to be my personal pensieve-bot.

The ASR model exploration can be found in this STT-exploratory gist and in particular this implementation is based on OpenAI's whisper model

The bot integration uses pyTelegramBotAPI

ToC

How To

Install

NOTE: It is recommended to create a virtual env with python 3.8+

pip install -r requirements.txt

Run

First create a .env file with the following values:

VALID_SENDER_IDS="sender_id_1,sender_id_2,..."  # telegram user IDs to which the bot replies
BOT_TOKEN="your-bot-token"  # Telgram bot token (from BotFather)

The run with:

# Run the bot with the 'small' whisper model
python -m src.run -m small -v INFO

About

A telegram bot to serve as a pensieve box from audio clips

Resources

Stars

Watchers

Forks

Packages

No packages published