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
120 lines
2.8 KiB
TOML
120 lines
2.8 KiB
TOML
[project]
|
|
name = "reflector"
|
|
version = "0.1.0"
|
|
description = ""
|
|
authors = [{ name = "Monadical team", email = "ops@monadical.com" }]
|
|
requires-python = ">=3.11, <3.13"
|
|
readme = "README.md"
|
|
dependencies = [
|
|
"aiohttp>=3.9.0",
|
|
"aiohttp-cors>=0.7.0",
|
|
"av>=10.0.0",
|
|
"requests>=2.31.0",
|
|
"aiortc>=1.5.0",
|
|
"sortedcontainers>=2.4.0",
|
|
"loguru>=0.7.0",
|
|
"pydantic-settings>=2.0.2",
|
|
"structlog>=23.1.0",
|
|
"uvicorn[standard]>=0.23.1",
|
|
"fastapi[standard]>=0.100.1",
|
|
"sentry-sdk[fastapi]>=1.29.2",
|
|
"httpx>=0.24.1",
|
|
"fastapi-pagination>=0.12.6",
|
|
"databases[aiosqlite, asyncpg]>=0.7.0",
|
|
"sqlalchemy<1.5",
|
|
"alembic>=1.11.3",
|
|
"nltk>=3.8.1",
|
|
"prometheus-fastapi-instrumentator>=6.1.0",
|
|
"sentencepiece>=0.1.99",
|
|
"protobuf>=4.24.3",
|
|
"profanityfilter>=2.0.6",
|
|
"celery>=5.3.4",
|
|
"redis>=5.0.1",
|
|
"python-jose[cryptography]>=3.3.0",
|
|
"python-multipart>=0.0.6",
|
|
"transformers>=4.36.2",
|
|
"jsonschema>=4.23.0",
|
|
"openai>=1.59.7",
|
|
"psycopg2-binary>=2.9.10",
|
|
"llama-index>=0.12.52",
|
|
"llama-index-llms-openai-like>=0.4.0",
|
|
"pytest-env>=1.1.5",
|
|
"webvtt-py>=0.5.0",
|
|
"silero-vad>=5.1.2",
|
|
]
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"black>=24.1.1",
|
|
"stamina>=23.1.0",
|
|
"pyinstrument>=4.6.1",
|
|
]
|
|
tests = [
|
|
"pytest-cov>=4.1.0",
|
|
"pytest-aiohttp>=1.0.4",
|
|
"pytest-asyncio>=0.21.1",
|
|
"pytest>=7.4.0",
|
|
"httpx-ws>=0.4.1",
|
|
"pytest-httpx>=0.23.1",
|
|
"pytest-celery>=0.0.0",
|
|
"pytest-recording>=0.13.4",
|
|
"pytest-docker>=3.2.3",
|
|
"asgi-lifespan>=2.1.0",
|
|
]
|
|
aws = ["aioboto3>=11.2.0"]
|
|
evaluation = [
|
|
"jiwer>=3.0.2",
|
|
"levenshtein>=0.21.1",
|
|
"tqdm>=4.66.0",
|
|
"pydantic>=2.1.1",
|
|
]
|
|
local = [
|
|
"pyannote-audio>=3.3.2",
|
|
"faster-whisper>=0.10.0",
|
|
]
|
|
|
|
[tool.uv]
|
|
default-groups = [
|
|
"dev",
|
|
"tests",
|
|
"aws",
|
|
"evaluation",
|
|
"local"
|
|
]
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["reflector"]
|
|
|
|
[tool.coverage.run]
|
|
source = ["reflector"]
|
|
|
|
[tool.pytest_env]
|
|
ENVIRONMENT = "pytest"
|
|
DATABASE_URL = "postgresql://test_user:test_password@localhost:15432/reflector_test"
|
|
|
|
[tool.pytest.ini_options]
|
|
addopts = "-ra -q --disable-pytest-warnings --cov --cov-report html -v"
|
|
testpaths = ["tests"]
|
|
asyncio_mode = "auto"
|
|
markers = [
|
|
"gpu_modal: mark test to run only with GPU Modal endpoints (deselect with '-m \"not gpu_modal\"')",
|
|
]
|
|
|
|
[tool.ruff.lint]
|
|
select = [
|
|
"I", # isort - import sorting
|
|
"F401", # unused imports
|
|
"PLC0415", # import-outside-top-level - detect inline imports
|
|
]
|
|
|
|
[tool.ruff.lint.per-file-ignores]
|
|
"reflector/processors/summary/summary_builder.py" = ["E501"]
|
|
"gpu/**.py" = ["PLC0415"]
|
|
"reflector/tools/**.py" = ["PLC0415"]
|
|
"migrations/versions/**.py" = ["PLC0415"]
|
|
"tests/**.py" = ["PLC0415"]
|