mirror of
https://github.com/Monadical-SAS/reflector.git
synced 2026-04-11 08:06:54 +00:00
a682846645
* fix: local processing instead of http server for cpu * add fallback token if service worker doesnt work * chore: rename processors to keep processor pattern up to date and allow other processors to be createed and used with env vars
38 lines
1.3 KiB
Python
38 lines
1.3 KiB
Python
"""
|
|
Pyannote audio diarization processor using pyannote.audio in-process.
|
|
|
|
Downloads audio from URL, runs pyannote diarization locally,
|
|
and returns speaker segments. No HTTP backend needed.
|
|
"""
|
|
|
|
import asyncio
|
|
import os
|
|
|
|
from reflector.processors._audio_download import download_audio_to_temp
|
|
from reflector.processors._pyannote_diarization_service import diarization_service
|
|
from reflector.processors.audio_diarization import AudioDiarizationProcessor
|
|
from reflector.processors.audio_diarization_auto import AudioDiarizationAutoProcessor
|
|
from reflector.processors.types import AudioDiarizationInput
|
|
|
|
|
|
class AudioDiarizationPyannoteProcessor(AudioDiarizationProcessor):
|
|
INPUT_TYPE = AudioDiarizationInput
|
|
|
|
async def _diarize(self, data: AudioDiarizationInput):
|
|
"""Run pyannote diarization on audio from URL."""
|
|
tmp_path = await download_audio_to_temp(data.audio_url)
|
|
try:
|
|
loop = asyncio.get_event_loop()
|
|
result = await loop.run_in_executor(
|
|
None, diarization_service.diarize_file, str(tmp_path)
|
|
)
|
|
return result["diarization"]
|
|
finally:
|
|
try:
|
|
os.unlink(tmp_path)
|
|
except OSError:
|
|
pass
|
|
|
|
|
|
AudioDiarizationAutoProcessor.register("pyannote", AudioDiarizationPyannoteProcessor)
|