mirror of
https://github.com/nomadkaraoke/karaoke-gen.git
synced 2026-11-20 13:07:57 +09:00
@coderabbitai ignore ## Why BACKLOG "audio-separator 0.45–0.47 regression: mel-band RoFormer karaoke models 3–5× slower on L4". The root cause is **python-audio-separator #299 (0.47.0)**, not #298. #299 made RoFormer `overlap` a *window count* that defaults to each model YAML's `num_overlap`. Before that, `overlap` was effectively an 8-second step, which meant almost no overlap. The karaoke models' YAMLs set `num_overlap` 4/8, so a 3-minute track went from 23 forward passes to 87 (aufr33) and 124 (gabox_v2, becruily). That matches the measured 25→75s, 26→149s and 27→157s. 0.45.0 and 0.46.0 still had the old step formula. python-audio-separator #313 (released as **0.47.1**) keeps #299. It adds a per-model forward-pass budget test on every PR and a GPU per-pass timing test (T4: 1.21 s/pass), plus a README note. Andrew chose overlap=2 for gen: smoother chunk seams than 0.44's no-overlap, at about 1.5× the 0.44 compute instead of 4–6×. ## What - `karaoke_gen/audio_processor.py`: `SEPARATOR_MDXC_PARAMS` (overlap=2) goes to all four `Separator(...)` constructions (stage 1, stage 2 karaoke ensemble, single-model paths) **only when audio-separator ≥ 0.47**. On older versions `overlap=2` meant a 2-second step, which is 4× slower, so they keep their defaults. Ensembles load each model through `load_model`, so the param reaches every model in the preset. - `backend/Dockerfile.gpu-base`: `AUDIO_SEPARATOR_VERSION=0.47.1`, with the comment rewritten to explain the root cause. 0.47.1 needs `torch>=2.3` on Linux, so the pre-installed `torch==2.6.0+cu126` (required by the L4 driver) is kept. - The poetry lock stays on 0.44.1. The version-aware params keep CI and CPU images on the old semantics, and there's no torch churn. ## Expected cost per ~3-min track (forward passes) | model | 0.44.2 | 0.47 YAML default | 0.47 + overlap=2 | |---|---|---|---| | karaoke_aufr33 | 23 | 87 | 44 | | karaoke_gabox_v2 | 23 | 124 | 32 | | karaoke_becruily | 23 | 124 | 32 | | instrumental fv7z / resurrection | 23 | 32 / 21 | 32 / 21 | ## Verification plan (before /backlog-finish) After the deploy, time the separation of the daily E2E or a real job on the audio-separation-job logs. I expect roughly 1.5× the 0.44.2 karaoke-stage times (~40–50s per karaoke model rather than 75–157s). If it's worse, revert the pin to 0.44.2. That's one line. ## Testing - `tests/unit/test_audio_processor_local_gpu.py`: version gating (0.47.x/0.48/1.0 → overlap 2; 0.44/0.46 → defaults; unknown → defaults; fresh copy), and both stages' constructors receive `mdxc_params.overlap == 2`. - `make test`: the backend unit suite passes. The only failures are 8 `test_emulator_integration.py` tests, caused by my local environment: another session's emulator setup is on :8080/:4443, and they fail identically on untouched main. CI is green on main. - Local CodeRabbit: 0 findings. 🤖 Generated with [Claude Code](https://claude.com/claude-code) https://claude.ai/code/session_01Jw21syo4HizJJjYw2mg2Vp --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
205 lines
6.9 KiB
TOML
205 lines
6.9 KiB
TOML
[tool.poetry]
|
|
name = "karaoke-gen"
|
|
version = "0.278.16"
|
|
description = "Generate karaoke videos with synchronized lyrics. Handles the entire process from downloading audio and lyrics to creating the final video with title screens."
|
|
authors = ["Andrew Beveridge <andrew@beveridge.uk>"]
|
|
license = "MIT"
|
|
readme = "README.md"
|
|
packages = [
|
|
{ include = "karaoke_gen" },
|
|
{ include = "backend" }
|
|
]
|
|
include = [
|
|
# The Next.js static export is generated at build time and gitignored (see #876).
|
|
# Poetry's plain-string include respects .gitignore and would DROP a gitignored
|
|
# path from the wheel; the dict form with an explicit `format` overrides .gitignore
|
|
# so the built frontend is still bundled (needed for the CLI local-review UI).
|
|
# Wheel-only: the sdist would balloon past PyPI's 10 GB cap, so bundle in the wheel only.
|
|
{ path = "karaoke_gen/nextjs_frontend/out/**/*", format = ["wheel"] },
|
|
"karaoke_gen/lyrics_transcriber/output/fonts/*",
|
|
"karaoke_gen/lyrics_transcriber/output/cdgmaker/images/*",
|
|
"karaoke_gen/lyrics_transcriber/output/cdgmaker/transitions/*",
|
|
# Skip/include lists for the YouTube description backfill worker (must ship in
|
|
# the Cloud Run image so the scheduled worker can read them).
|
|
"backend/data/youtube_backfill/*.txt"
|
|
]
|
|
homepage = "https://github.com/nomadkaraoke/karaoke-gen"
|
|
repository = "https://github.com/nomadkaraoke/karaoke-gen"
|
|
documentation = "https://github.com/nomadkaraoke/karaoke-gen/blob/main/README.md"
|
|
|
|
[tool.poetry.dependencies]
|
|
python = ">=3.10,<3.14"
|
|
torch = ">=2.7"
|
|
requests = ">=2"
|
|
beautifulsoup4 = ">=4"
|
|
flacfetch = ">=0.9.0"
|
|
lyricsgenius = ">=3"
|
|
fetch-lyrics-from-genius = ">=0.1"
|
|
pillow = ">=10.1"
|
|
pyinstaller = ">=6.3"
|
|
google-api-python-client = "2.193.0"
|
|
google-auth = "2.49.1"
|
|
google-auth-oauthlib = "1.3.0"
|
|
google-auth-httplib2 = "0.3.0"
|
|
thefuzz = ">=0.22"
|
|
numpy = ">=2"
|
|
audio-separator = { version = ">=0.43.0", extras = ["cpu"] }
|
|
lyrics-converter = ">=0.2.1"
|
|
# lyrics_transcriber is now a subpackage of karaoke_gen (karaoke_gen/lyrics_transcriber/)
|
|
# Dependencies from vendored lyrics_transcriber:
|
|
mutagen = ">=1.47" # For LRCLIB provider to get track duration for better matching
|
|
python-slugify = ">=8"
|
|
syrics = ">=0"
|
|
karaoke-lyrics-processor = ">=0.6"
|
|
dropbox = ">=12"
|
|
spacy = ">=3.8.7"
|
|
srsly = ">=2.5.1"
|
|
tqdm = ">=4.67"
|
|
python-levenshtein = ">=0.26"
|
|
transformers = ">=4.47"
|
|
metaphone = ">=0.6"
|
|
nltk = ">=3.9"
|
|
spacy-syllables = ">=3"
|
|
syllables = ">=1"
|
|
fonttools = ">=4.55"
|
|
ollama = ">=0.4.7"
|
|
shortuuid = ">=1.0.13"
|
|
nest-asyncio = ">=1.5"
|
|
openai = ">=1.63.2"
|
|
langgraph = ">=0.2.0"
|
|
langchain = ">=0.3.0"
|
|
langchain-core = ">=0.3.0"
|
|
langchain-openai = ">=0.2.0"
|
|
langchain-anthropic = ">=0.2.0"
|
|
anthropic = ">=0.109.0" # direct dep: auto-correct structured outputs (output_config)
|
|
langchain-ollama = ">=0.2.0"
|
|
langchain-google-genai = ">=2.0.0"
|
|
langfuse = ">=3.0.0"
|
|
jiwer = ">=3.0.0"
|
|
kbputils = "^0.0.16"
|
|
attrs = ">=24.2.0"
|
|
cattrs = ">=24.1.2"
|
|
toml = ">=0.10"
|
|
argparse = ">=1.4.0"
|
|
psutil = "^7.0.0"
|
|
pyperclip = "*"
|
|
pytest-asyncio = "*"
|
|
ffmpeg-python = "^0.2.0"
|
|
python-multipart = "^0.0.20"
|
|
python-docx = ">=1.1.0"
|
|
yt-dlp = ">=2024.0.0"
|
|
matplotlib = ">=3"
|
|
# Backend API dependencies
|
|
fastapi = ">=0.104.0"
|
|
uvicorn = { version = ">=0.24.0", extras = ["standard"] }
|
|
pydantic = ">=2.5.0"
|
|
pydantic-settings = ">=2.1.0"
|
|
httpx = ">=0.25.0"
|
|
tenacity = "^8.2.0" # Retry logic for external service calls
|
|
google-cloud-firestore = "2.26.0"
|
|
google-cloud-compute = "^1.0.0"
|
|
google-cloud-storage = "3.10.1"
|
|
google-cloud-secret-manager = "2.26.0"
|
|
google-cloud-monitoring = "2.29.1" # Cloud Monitoring for YouTube API quota metrics
|
|
google-cloud-tasks = "2.21.0" # Cloud Tasks for worker coordination (Phase 1 scalability)
|
|
google-cloud-run = "0.15.0" # Cloud Run Jobs for long-running video encoding (Phase 2 scalability)
|
|
google-cloud-logging = ">=3.9.0" # Cloud Logging for error monitoring
|
|
python-dotenv = ">=1.0.0"
|
|
pydub = ">=0.25.1"
|
|
# Google / Apple ID-token verification (JWKS) for mobile sign-in
|
|
pyjwt = { version = ">=2.8.0", extras = ["crypto"] }
|
|
# Payment and email services
|
|
stripe = "^14.1.0"
|
|
email-validator = ">=2.0.0" # For Pydantic EmailStr validation
|
|
# Web Push notifications
|
|
pywebpush = ">=2.0.0"
|
|
# OpenTelemetry for distributed tracing
|
|
opentelemetry-api = ">=1.20.0"
|
|
opentelemetry-sdk = ">=1.20.0"
|
|
opentelemetry-instrumentation-fastapi = ">=0.41b0"
|
|
opentelemetry-instrumentation-httpx = ">=0.41b0"
|
|
opentelemetry-instrumentation-logging = ">=0.41b0"
|
|
opentelemetry-exporter-gcp-trace = ">=1.6.0"
|
|
opentelemetry-resourcedetector-gcp = ">=1.6.0a0"
|
|
# Optional: Local Whisper transcription (install with: pip install karaoke-gen[local-whisper])
|
|
whisper-timestamped = { version = ">=1.15.0", optional = true }
|
|
aiohttp = "^3.13.2"
|
|
|
|
[tool.poetry.group.dev.dependencies]
|
|
black = ">=23"
|
|
poetry = "*"
|
|
pytest = ">=7.0"
|
|
pytest-cov = ">=4.0"
|
|
pytest-mock = ">=3.10"
|
|
pytest-asyncio = "*"
|
|
|
|
# Make dev dependencies available as optional extras for pip install
|
|
# These need to be declared as optional dependencies first
|
|
[tool.poetry.dependencies.black]
|
|
version = ">=23"
|
|
optional = true
|
|
|
|
[tool.poetry.dependencies.pytest]
|
|
version = ">=7.0"
|
|
optional = true
|
|
|
|
[tool.poetry.dependencies.pytest-cov]
|
|
version = ">=4.0"
|
|
optional = true
|
|
|
|
[tool.poetry.dependencies.pytest-mock]
|
|
version = ">=3.10"
|
|
optional = true
|
|
|
|
[tool.poetry.extras]
|
|
# Local Whisper transcription support - optional, heavy dependencies
|
|
# Install with: pip install karaoke-gen[local-whisper]
|
|
# For CPU-only installation (recommended for systems without GPU):
|
|
# pip install torch torchaudio --index-url https://download.pytorch.org/whl/cpu
|
|
# pip install karaoke-gen[local-whisper]
|
|
local-whisper = ["whisper-timestamped"]
|
|
|
|
# Development/testing dependencies (pytest-asyncio is already a main dependency)
|
|
# Install with: pip install -e ".[dev]" or pip install -e ".[local-whisper,dev]"
|
|
dev = ["black", "pytest", "pytest-cov", "pytest-mock"]
|
|
|
|
[tool.poetry.scripts]
|
|
karaoke-gen = 'karaoke_gen.utils.gen_cli:main'
|
|
karaoke-gen-remote = 'karaoke_gen.utils.remote_cli:main'
|
|
karaoke-bulk = 'karaoke_gen.utils.bulk_cli:main'
|
|
|
|
[tool.black]
|
|
line-length = 140
|
|
|
|
[build-system]
|
|
requires = ["poetry-core"]
|
|
build-backend = "poetry.core.masonry.api"
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests/unit", "tests/integration", "backend/tests"]
|
|
python_files = ["test_*.py"]
|
|
addopts = [
|
|
"--asyncio-mode=auto",
|
|
"-v",
|
|
"--tb=short",
|
|
]
|
|
markers = [
|
|
"slow: marks tests as slow (deselect with '-m \"not slow\"')",
|
|
"integration: marks tests as integration tests",
|
|
"asyncio: mark test as async",
|
|
"emulator: marks tests requiring GCP emulators",
|
|
]
|
|
filterwarnings = [
|
|
"ignore::DeprecationWarning",
|
|
"ignore:'audioop' is deprecated:DeprecationWarning",
|
|
"ignore::RuntimeWarning",
|
|
"ignore::UserWarning",
|
|
]
|
|
|
|
[tool.coverage.run]
|
|
# Exclude lyrics_transcriber subpackage from coverage since it was a separate vendored package
|
|
# with its own test suite - including it in karaoke_gen coverage would unfairly lower the percentage
|
|
omit = [
|
|
"karaoke_gen/lyrics_transcriber/*",
|
|
]
|