faster-whisper-server 0.0.1

OpenAI-compatible FastAPI server for faster-whisper.

Faster-Whisper-Server

Overview

FastAPI server for OpenAI-compatible audio transcription and translation using faster-whisper. Supports single-model or multi-model hosting.

Install

uv pip install -e .

Run (single model)

faster-whisper-server small --reload

Run (multi-model config)

faster-whisper-server --config /path/to/config.yaml --reload

Example config:

models:
	- name: whisper-1
		path: small
		transcribe_options:
			beam_size: 5
			vad_filter: true
	- name: large-fast
		path: /models/large-v3
		translate_options:
			temperature: 0.2

API usage

Transcription:

curl -X POST "http://localhost:8000/v1/audio/transcriptions" \
	-F "file=@/path/to/audio.wav" \
	-F "model=whisper-1" \
	-F "response_format=json"

Translation:

curl -X POST "http://localhost:8000/v1/audio/translations" \
	-F "file=@/path/to/audio.wav" \
	-F "model=whisper-1" \
	-F "response_format=json"

Health check:

curl "http://localhost:8000/health"

Notes

• When running with a config file, the request model must match a config name entry.
• --log-level controls only the faster-whisper-server logger and defaults to warning.