Function transcribe

examples/openai_api/server.py:91–157

OpenAI-compatible audio transcription endpoint. Accepts the same parameters as OpenAI's /v1/audio/transcriptions: - file: Audio file (wav, mp3, flac, m4a, ogg, webm) - model: Model to use (sensevoice, paraformer, fun-asr-nano) - language: Optional language hint - respon

(
    file: UploadFile = File(...),
    model: str = Form(default="sensevoice"),
    language: Optional[str] = Form(default=None),
    response_format: Optional[str] = Form(default="json"),
)

@app.post("/v1/audio/transcriptions")
async def transcribe(
    file: UploadFile = File(...),
    model: str = Form(default="sensevoice"),
    language: Optional[str] = Form(default=None),
    response_format: Optional[str] = Form(default="json"),
):
    """
    OpenAI-compatible audio transcription endpoint.
    
    Accepts the same parameters as OpenAI's /v1/audio/transcriptions:
    - file: Audio file (wav, mp3, flac, m4a, ogg, webm)
    - model: Model to use (sensevoice, paraformer, fun-asr-nano)
    - language: Optional language hint
    - response_format: json or verbose_json
    """
    # Validate model
    if model not in MODEL_CONFIGS:
        raise HTTPException(
            status_code=400,
            detail=f"Model '{model}' not found. Available: {list(MODEL_CONFIGS.keys())}"
        )

    # Save uploaded file
    suffix = os.path.splitext(file.filename)[1] if file.filename else ".wav"
    with tempfile.NamedTemporaryFile(delete=False, suffix=suffix) as tmp:
        content = await file.read()
        tmp.write(content)
        tmp_path = tmp.name

    try:
        asr_model = load_model(model)
        t0 = time.time()

        generate_kwargs = {"input": tmp_path, "batch_size": 1}
        if language:
            generate_kwargs["language"] = language

        result = asr_model.generate(**generate_kwargs)
        elapsed = time.time() - t0

        text = clean_text(result[0]["text"])

        if response_format == "verbose_json":
            segments = []
            if "sentence_info" in result[0]:
                for seg in result[0]["sentence_info"]:
                    segments.append({
                        "start": seg.get("start", 0) / 1000.0,
                        "end": seg.get("end", 0) / 1000.0,
                        "text": clean_text(seg.get("text", "")),
                        "speaker": seg.get("spk", None),
                    })
            return JSONResponse({
                "text": text,
                "segments": segments,
                "language": language or "auto",
                "duration": round(elapsed, 3),
                "model": model,