A Python + FastAPI web app that transcribes audio recordings using OpenAI Whisper. Supports multilingual transcription (including English and Hindi) and provides a beautiful web interface to upload and view results.

• ✅ Upload audio recordings (MP3, WAV, etc.)

A Python + FastAPI web app that transcribes audio recordings using OpenAI Whisper. Supports multilingual transcription (including English and Hindi) and provides a beautiful web interface with real-time progress tracking.

• ✅ Upload audio recordings (MP3, WAV, etc.)
• ✅ Youtube video transcription
• ✅ Transcribes audio using Whisper
• ✅ Supports English, Hindi & other languages
• ✅ Clean, responsive UI with multi-line output
• ✅ Dockerized for easy deployment
• ✅ GitHub Actions CI to auto-publish Docker image

• ✅ Transcribes audio using Whisper
• ✅ Supports English, Hindi & other languages
• ✅ Clean, responsive UI with multi-line output
• ✅ Dockerized for easy deployment
• ✅ GitHub Actions CI to auto-publish Docker image

• Backend: FastAPI, Whisper
• Frontend: HTML + CSS (Jinja2 templating)
• Container: Docker
• CI/CD: GitHub Actions

git clone https://github.com/Amrish-Sharma/ata.git
cd ata

pip install -r requirements.txt

uvicorn app.main:app --reload

Open in browser: http://localhost:8000

docker build -t audio-transcriber .
docker run -p 8000:8000 audio-transcriber

Visit: http://localhost:8000

This project includes a GitHub Action that automatically:

• Builds the Docker image
• Pushes it to GitHub Container Registry (GHCR) on every main push

Image will be available at:

ghcr.io/Amrish-Sharma/ata:latest

An Android app is in development to let users record or select audio and get transcriptions directly on their phones.

.
├── app/
│   ├── main.py         # FastAPI entrypoint
│   └── utils.py        # Whisper transcription logic
├── static/             # Static assets
│   ├── css/
│   │   ├── style.css   # Main stylesheet
│   └── js/
│       └── main.js     # Frontend logic & AJAX handlers
├── templates/
│   |── index.html      # UI frontend
|   |__ result.html     # result interface
├── uploads/            # Uploaded audio (gitignored)
├── Dockerfile
├── .gitignore
├── requirements.txt
└── README.md

Pull requests welcome! For major changes, please open an issue first to discuss what you'd like to change.

MIT License

• OpenAI Whisper
• FastAPI
• GitHub Actions