https://github.com/chinese-soup/cbot-telegram-whisper

Simple bot that transcribes Telegram voice messages. Powered by go-telegram-bot-api & whisper.cpp Go bindings.
https://github.com/chinese-soup/cbot-telegram-whisper

bot cpu-inference golang openai speech-recognition speech-to-text whisper whisper-cpp whispercpp

Last synced: 6 days ago
JSON representation

Simple bot that transcribes Telegram voice messages. Powered by go-telegram-bot-api & whisper.cpp Go bindings.

• Host: GitHub
• URL: https://github.com/chinese-soup/cbot-telegram-whisper
• Owner: chinese-soup
• Created: 2023-04-19T16:41:41.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2023-04-19T17:32:41.000Z (almost 2 years ago)
• Last Synced: 2025-01-11T15:12:11.996Z (12 days ago)
• Topics: bot, cpu-inference, golang, openai, speech-recognition, speech-to-text, whisper, whisper-cpp, whispercpp
• Language: Go
• Homepage:
• Size: 12.7 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# cbot-telegram-whisper

Quick and dirty bot (or more of a PoC) that transcribes Telegram voice messages using OpenAI's whisper models, using CPU inference thanks to [whisper.cpp](https://github.com/ggerganov/whisper.cpp) 

## Built using: 

* [go-telegram-bot-api](https://pkg.go.dev/github.com/go-telegram-bot-api/telegram-bot-api/v5) 

* [whisper.cpp Go bindings](https://github.com/ggerganov/whisper.cpp/tree/master/bindings/go/)

* [u2takey's ffmpeg-go](https://github.com/u2takey/ffmpeg-go)

* [grab](https://github.com/cavaliergopher/grab) 

## TODO

* refactor

* possibly get rid of ffmpeg lib? 

* fix error handling & generating

## How to build

#### You can check out the example [Dockerfile](Dockerfile), but TL;DR:

```bash

git clone [email protected]:chinese-soup/cbot-telegram-whisper.git && \

cd cbot-telegram-whisper && \

git clone https://github.com/ggerganov/whisper.cpp.git && \

cd whisper.cpp/bindings/go && \

make whisper && \

cd ../../.. && \

go get

C_INCLUDE_PATH=/app/whisper.cpp/ LIBRARY_PATH=/app/whisper.cpp/ go build -o whisperbot

```

#### Get a model, e.g.:

```bash

bash whisper.cpp/models/download-ggml-model.sh tiny.en

```

Check out [whisper.cpp's](https://github.com/ggerganov/whisper.cpp) README for more info.

#### Set the environment variables mentioned in `.env.example`, e.g.:

```bash

export TELEGRAM_APITOKEN=

export MODELPATH=whisper.cpp/models/ggml-tiny.en.bin

```

#### Make sure ffmpeg is in $PATH:

```bash

$ which ffmpeg

/usr/bin/ffmpeg

```

If it isn't install a binary or compile and put it in path.

#### And you're all set, run it:

```bash

./whisperbot

```