whisper-stt-chatbot/app.py

from fastapi import FastAPI, UploadFile, File
from faster_whisper import WhisperModel
import tempfile
import os

app = FastAPI()

model = WhisperModel(
    "small",
    device="cuda",
    compute_type="float16"
)

@app.post("/transcribe")
async def transcribe(file: UploadFile = File(...)):
    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp:
        tmp.write(await file.read())
        tmp_path = tmp.name

    segments, info = model.transcribe(
        tmp_path,
        language="fr",
        vad_filter=True
    )

    os.remove(tmp_path)

    text = " ".join([seg.text for seg in segments])

    return {
        "text": text,
        "language": info.language
    }