3cx-telefonie-middleware/app/whisper.py

from __future__ import annotations

from pathlib import Path
from typing import Any


class WhisperWorker:
    """
    Langlebiger Whisper-Worker.

    Das Modell wird genau einmal geladen.
    """

    def __init__(self, settings):
        self.settings = settings
        self.model = None

    def start(self):
        from faster_whisper import WhisperModel

        self.model = WhisperModel(
            self.settings.whisper_model,
            device=self.settings.whisper_device,
            compute_type=self.settings.whisper_compute_type,
        )

    def transcribe(
        self,
        audio: str | Path,
    ) -> dict[str, Any]:

        if self.model is None:
            self.start()

        segments, info = self.model.transcribe(
            str(audio),
            language=self.settings.whisper_language,
            vad_filter=True,
        )

        result_segments = []

        for segment in segments:
            text = segment.text.strip()

            if not text:
                continue

            result_segments.append(
                {
                    "start": segment.start,
                    "end": segment.end,
                    "text": text,
                }
            )

        text = " ".join(
            item["text"]
            for item in result_segments
        )

        return {
            "language": info.language,
            "language_probability": info.language_probability,
            "text": text,
            "segments": result_segments,
        }