innovatorved/whisper.api

This project provides an API with user level access support to transcribe speech to text using a finetuned and processed Whisper ASR model.

55
/ 100
Established

Implements asynchronous transcription with built-in concurrency control and request queuing via a FastAPI-based HTTP API, supporting quantized model variants (tiny.en.q5, base.en.q5) for efficient inference. Includes ffmpeg audio processing, token-based authentication for user access management, and Docker containerization for self-hosted deployment. The architecture uses uvicorn as the ASGI server with configurable parallel job limits via environment variables.

914 stars. Actively maintained with 22 commits in the last 30 days.

No Package No Dependents
Maintenance 16 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

914

Forks

38

Language

Python

License

MIT

Last pushed

Jan 02, 2026

Commits (30d)

22

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/innovatorved/whisper.api"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.