Hugging Face's logo

Spaces:
pmmdot
/
whispr
Sleeping

App Files Community
whispr / README.md
pmmdot's picture
pmmdot
Final touchups!
2ecaacb
preview code
|
raw
history blame contribute delete
1.2 kB
metadata 
title: Whispr
emoji: 🎙️
colorFrom: yellow
colorTo: red
sdk: docker
app_port: 7860
pinned: false

Whispr

Open in Spaces Docker Python Whisper

A web-based speech transcription service powered by OpenAI's Whisper model. Upload audio and get instant text transcription.

🚀 Try it live

Live demo: https://huggingface.co/spaces/dotpmm/whispr

How it works

  • FastAPI backend serves a web interface and transcription API
  • Whisper model (base, int8) runs locally on CPU for privacy
  • Web interface lets you record or upload audio files
  • REST API at /transcribe accepts audio uploads

Quick start

Run locally:

pip install -r requirements.txt
uvicorn main:app --reload

Or with Docker:

docker build -t whispr .
docker run -p 7860:7860 whispr

Open http://localhost:7860 and start transcribing!