model-ml/ml-api/app/stt.py

from pathlib import Path
from typing import Tuple
import tempfile
import subprocess

import whisper


_WHISPER_MODEL = None


def _get_model(name: str = "base"):
    global _WHISPER_MODEL
    if _WHISPER_MODEL is None:
        _WHISPER_MODEL = whisper.load_model(name)
    return _WHISPER_MODEL


def ensure_wav(input_path: Path) -> Path:
    """Convertit l'audio en WAV si nécessaire via ffmpeg."""
    if input_path.suffix.lower() == ".wav":
        return input_path
    out = Path(tempfile.mkstemp(suffix=".wav")[1])
    cmd = [
        "ffmpeg",
        "-i",
        str(input_path),
        "-ar",
        "16000",
        "-ac",
        "1",
        str(out),
        "-y",
    ]
    subprocess.run(cmd, check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
    return out


def transcribe(audio_path: Path) -> Tuple[str, str]:
    """
    Transcrit le fichier audio avec Whisper.
    Retourne (texte, langue_detectee_par_whisper).
    """
    model = _get_model()
    wav_path = ensure_wav(audio_path)
    result = model.transcribe(str(wav_path))
    text = result.get("text", "").strip()
    lang = result.get("language", "")  # e.g., 'fr'
    return text, lang