#
# Copyright (c) 2024-2026, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

import asyncio
import sys

from dotenv import load_dotenv
from loguru import logger

from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import Frame, InterimTranscriptionFrame, TranscriptionFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.worker import PipelineWorker, ProcessorUnusablePolicy
from pipecat.processors.audio.vad_processor import VADProcessor
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.services.whisper.stt import WhisperSTTService
from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
from pipecat.workers.runner import WorkerRunner

load_dotenv(override=True)

logger.remove(0)
logger.add(sys.stderr, level="DEBUG")


class TranscriptionLogger(FrameProcessor):
    async def process_frame(self, frame: Frame, direction: FrameDirection):
        await super().process_frame(frame, direction)

        if isinstance(frame, TranscriptionFrame):
            print(f"Transcription: {frame.text}")
        elif isinstance(frame, InterimTranscriptionFrame):
            print(f"Interim transcription: {frame.text}")

        # Push all frames through
        await self.push_frame(frame, direction)


async def main():
    transport = LocalAudioTransport(
        LocalAudioTransportParams(
            audio_in_enabled=True,
        )
    )

    stt = WhisperSTTService()

    tl = TranscriptionLogger()

    vad_processor = VADProcessor(vad_analyzer=SileroVADAnalyzer())

    pipeline = Pipeline([transport.input(), vad_processor, stt, tl, transport.output()])

    worker = PipelineWorker(pipeline, processor_unusable_policy=ProcessorUnusablePolicy.END)

    runner = WorkerRunner(handle_sigint=False if sys.platform == "win32" else True)

    await runner.add_workers(worker)
    await runner.run()


if __name__ == "__main__":
    asyncio.run(main())