mirror of
https://github.com/Monadical-SAS/reflector.git
synced 2025-12-20 20:29:06 +00:00
Mathieu Virbel
3ea7f6b7b6
* feat: improve pipeline threading, and transcriber (parakeet and silero vad) * refactor: remove whisperx, implement parakeet * refactor: make audio_chunker more smart and wait for speech, instead of fixed frame * refactor: make audio merge to always downscale the audio to 16k for transcription * refactor: make the audio transcript modal accepting batches * refactor: improve type safety and remove prometheus metrics - Add DiarizationSegment TypedDict for proper diarization typing - Replace List/Optional with modern Python list/| None syntax - Remove all Prometheus metrics from TranscriptDiarizationAssemblerProcessor - Add comprehensive file processing pipeline with parallel execution - Update processor imports and type annotations throughout - Implement optimized file pipeline as default in process.py tool * refactor: convert FileDiarizationProcessor I/O types to BaseModel Update FileDiarizationInput and FileDiarizationOutput to inherit from BaseModel instead of plain classes, following the standard pattern used by other processors in the codebase. * test: add tests for file transcript and diarization with pytest-recording * build: add pytest-recording * feat: add local pyannote for testing * fix: replace PyAV AudioResampler with torchaudio for reliable audio processing - Replace problematic PyAV AudioResampler that was causing ValueError: [Errno 22] Invalid argument - Use torchaudio.functional.resample for robust sample rate conversion - Optimize processing: skip conversion for already 16kHz mono audio - Add direct WAV writing with Python wave module for better performance - Consolidate duplicate downsample checks for cleaner code - Maintain list[av.AudioFrame] input interface - Required for Silero VAD which needs 16kHz mono audio * fix: replace PyAV AudioResampler with torchaudio solution - Resolves ValueError: [Errno 22] Invalid argument in AudioMergeProcessor - Replaces problematic PyAV AudioResampler with torchaudio.functional.resample - Optimizes processing to skip unnecessary conversions when audio is already 16kHz mono - Uses direct WAV writing with Python's wave module for better performance - Fixes test_basic_process to disable diarization (pyannote dependency not installed) - Updates test expectations to match actual processor behavior - Removes unused pydub dependency from pyproject.toml - Adds comprehensive TEST_ANALYSIS.md documenting test suite status * feat: add parameterized test for both diarization modes - Adds @pytest.mark.parametrize to test_basic_process with enable_diarization=[False, True] - Test with diarization=False always passes (tests core AudioMergeProcessor functionality) - Test with diarization=True gracefully skips when pyannote.audio is not installed - Provides comprehensive test coverage for both pipeline configurations * fix: resolve pipeline property naming conflict in AudioDiarizationPyannoteProcessor - Renames 'pipeline' property to 'diarization_pipeline' to avoid conflict with base Processor.pipeline attribute - Fixes AttributeError: 'property 'pipeline' object has no setter' when set_pipeline() is called - Updates property usage in _diarize method to use new name - Now correctly supports pipeline initialization for diarization processing * fix: add local for pyannote * test: add diarization test * fix: resample on audio merge now working * fix: correctly restore timestamp * fix: display exception in a threaded processor if that happen * Update pyproject.toml * ci: remove option * ci: update astral-sh/setup-uv * test: add monadical url for pytest-recording * refactor: remove previous version * build: move faster whisper to local dep * test: fix missing import * refactor: improve main_file_pipeline organization and error handling - Move all imports to the top of the file - Create unified EmptyPipeline class to replace duplicate mock pipeline code - Remove timeout and fallback logic - let processors handle their own retries - Fix error handling to raise any exception from parallel tasks - Add proper type hints and validation for captured results * fix: wrong function * fix: remove task_done * feat: add configurable file processing timeouts for modal processors - Add TRANSCRIPT_FILE_TIMEOUT setting (default: 600s) for file transcription - Add DIARIZATION_FILE_TIMEOUT setting (default: 600s) for file diarization - Replace hardcoded timeout=600 with configurable settings in modal processors - Allows customization of timeout values via environment variables * fix: use logger * fix: worker process meetings now use file pipeline * fix: topic not gathered * refactor: remove prepare(), pipeline now work * refactor: implement many review from Igor * test: add test for test_pipeline_main_file * refactor: remove doc * doc: add doc * ci: update build to use native arm64 builder * fix: merge fixes * refactor: changes from Igor review + add test (not by default) to test gpu modal part * ci: update to our own runner linux-amd64 * ci: try using suggested mode=min * fix: update diarizer for latest modal, and use volume * fix: modal file extension detection * fix: put the diarizer as A100
75 lines
2.2 KiB
Python
75 lines
2.2 KiB
Python
"""
|
|
File transcription implementation using the GPU service from modal.com
|
|
|
|
API will be a POST request to TRANSCRIPT_URL:
|
|
|
|
```json
|
|
{
|
|
"audio_file_url": "https://...",
|
|
"language": "en",
|
|
"model": "parakeet-tdt-0.6b-v2",
|
|
"batch": true
|
|
}
|
|
```
|
|
"""
|
|
|
|
import httpx
|
|
|
|
from reflector.processors.file_transcript import (
|
|
FileTranscriptInput,
|
|
FileTranscriptProcessor,
|
|
)
|
|
from reflector.processors.file_transcript_auto import FileTranscriptAutoProcessor
|
|
from reflector.processors.types import Transcript, Word
|
|
from reflector.settings import settings
|
|
|
|
|
|
class FileTranscriptModalProcessor(FileTranscriptProcessor):
|
|
def __init__(self, modal_api_key: str | None = None, **kwargs):
|
|
super().__init__(**kwargs)
|
|
if not settings.TRANSCRIPT_URL:
|
|
raise Exception(
|
|
"TRANSCRIPT_URL required to use FileTranscriptModalProcessor"
|
|
)
|
|
self.transcript_url = settings.TRANSCRIPT_URL
|
|
self.file_timeout = settings.TRANSCRIPT_FILE_TIMEOUT
|
|
self.modal_api_key = modal_api_key
|
|
|
|
async def _transcript(self, data: FileTranscriptInput):
|
|
"""Send full file to Modal for transcription"""
|
|
url = f"{self.transcript_url}/v1/audio/transcriptions-from-url"
|
|
|
|
self.logger.info(f"Starting file transcription from {data.audio_url}")
|
|
|
|
headers = {}
|
|
if self.modal_api_key:
|
|
headers["Authorization"] = f"Bearer {self.modal_api_key}"
|
|
|
|
async with httpx.AsyncClient(timeout=self.file_timeout) as client:
|
|
response = await client.post(
|
|
url,
|
|
headers=headers,
|
|
json={
|
|
"audio_file_url": data.audio_url,
|
|
"language": data.language,
|
|
"batch": True,
|
|
},
|
|
)
|
|
response.raise_for_status()
|
|
result = response.json()
|
|
|
|
words = [
|
|
Word(
|
|
text=word_info["word"],
|
|
start=word_info["start"],
|
|
end=word_info["end"],
|
|
)
|
|
for word_info in result.get("words", [])
|
|
]
|
|
|
|
return Transcript(words=words)
|
|
|
|
|
|
# Register with the auto processor
|
|
FileTranscriptAutoProcessor.register("modal", FileTranscriptModalProcessor)
|