# SPDX-License-Identifier: GPL-3.0-only
"""Transcription providers.

- OpenAICompatibleTranscriber: any endpoint speaking the OpenAI /audio/transcriptions API -
  OpenAI Whisper, Groq (whisper-large-v3), or a self-hosted whisper.cpp/faster-whisper
  server exposing that route.
- LocalWhisperTranscriber: in-process faster-whisper. Wired up in M5 (needs the model
  download); the interface and config exist now so it is selectable.
"""
from __future__ import annotations

import os

import httpx

from ..models import Transcript, TranscriptSegment


class OpenAICompatibleTranscriber:
    def __init__(self, base_url: str, api_key: str, model: str):
        self.base_url = base_url.rstrip("/")
        self.api_key = api_key
        self.model = model
        self.name = f"openai_compatible:{model}"

    def transcribe(self, audio_path: str, language: str | None = None) -> Transcript:
        headers = {"Authorization": f"Bearer {self.api_key}"} if self.api_key else {}
        data = {"model": self.model, "response_format": "verbose_json"}
        if language:
            data["language"] = language
        with open(audio_path, "rb") as f:
            files = {"file": (os.path.basename(audio_path), f, "audio/wav")}
            resp = httpx.post(
                f"{self.base_url}/audio/transcriptions",
                headers=headers,
                data=data,
                files=files,
                timeout=600,
            )
        resp.raise_for_status()
        body = resp.json()
        segments = [
            TranscriptSegment(start=s.get("start", 0.0), end=s.get("end", 0.0),
                              text=s.get("text", ""))
            for s in body.get("segments", [])
        ]
        return Transcript(
            recording_id="",
            language=body.get("language") or language or "en",
            model=self.name,
            text=body.get("text", ""),
            segments=segments,
        )


class LocalWhisperTranscriber:
    def __init__(self, model: str, device: str, compute_type: str):
        self.model = model
        self.device = device
        self.compute_type = compute_type
        self.name = f"faster-whisper:{model}"

    def transcribe(self, audio_path: str, language: str | None = None) -> Transcript:
        # M5: load faster_whisper.WhisperModel(self.model, device, compute_type) and run it.
        raise NotImplementedError("Local faster-whisper transcription lands in M5")