Push rest

.gitignore

@@ -0,0 +1,62 @@
+# Byte-compiled / optimized / DLL files
+__pycache__
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# macOS dir files
+.DS_Store
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+.ipynb_checkpoints
+
+# Tests and linter
+.pytest_cache/
+.mypy_cache/
+.coverage
+
+# docs
+/api_docs
+
+# dotenv
+.env
+.envrc
+
+# virtualenv
+.venv
+venv/
+ENV/
+
+# egs with manifest files
+egs/*
+!egs/example
+# local datasets
+dataset/*
+!dataset/example
+
+# personal notebooks & scripts
+*/local_scripts
+*/notes
+.vscode/
+/notebooks
+/local_scripts
+/notes

MANIFEST.in

@@ -0,0 +1,15 @@
+include Makefile
+include LICENSE
+include LICENSE_weights
+include *.md
+include *.ini
+include requirements.txt
+include audiocraft/py.typed
+include assets/*.mp3
+include datasets/*.mp3
+recursive-include config *.yaml
+recursive-include demos *.py
+recursive-include demos *.ipynb
+recursive-include scripts *.py
+recursive-include model_cards *.md
+recursive-include docs *.md

Makefile

@@ -0,0 +1,40 @@
+INTEG=AUDIOCRAFT_DORA_DIR="/tmp/magma_$(USER)" python3 -m dora -v run --clear device=cpu dataset.num_workers=0 optim.epochs=1 \
+	dataset.train.num_samples=10 dataset.valid.num_samples=10 \
+	dataset.evaluate.num_samples=10 dataset.generate.num_samples=2 sample_rate=16000 \
+	logging.level=DEBUG
+INTEG_COMPRESSION = $(INTEG) solver=compression/debug rvq.n_q=2 rvq.bins=48 checkpoint.save_last=true   # SIG is 5091833e
+INTEG_MUSICGEN = $(INTEG) solver=musicgen/debug dset=audio/example compression_model_checkpoint=//sig/5091833e \
+	transformer_lm.n_q=2 transformer_lm.card=48 transformer_lm.dim=16 checkpoint.save_last=false  # Using compression model from 5091833e
+INTEG_AUDIOGEN = $(INTEG) solver=audiogen/debug dset=audio/example compression_model_checkpoint=//sig/5091833e \
+	transformer_lm.n_q=2 transformer_lm.card=48 transformer_lm.dim=16 checkpoint.save_last=false  # Using compression model from 5091833e
+INTEG_MBD = $(INTEG) solver=diffusion/debug dset=audio/example  \
+	checkpoint.save_last=false  # Using compression model from 616d7b3c
+
+default: linter tests
+
+install:
+	pip install -U pip
+	pip install -U -e '.[dev]'
+
+linter:
+	flake8 audiocraft && mypy audiocraft
+	flake8 tests && mypy tests
+
+tests:
+	coverage run -m pytest tests
+	coverage report
+
+tests_integ:
+	$(INTEG_COMPRESSION)
+	$(INTEG_MBD)
+	$(INTEG_MUSICGEN)
+	$(INTEG_AUDIOGEN)
+
+
+api_docs:
+	pdoc3 --html -o api_docs -f audiocraft
+
+dist:
+	python setup.py sdist
+
+.PHONY: linter tests api_docs dist

mypy.ini

@@ -0,0 +1,4 @@
+[mypy]
+
+[mypy-treetable,torchaudio.*,soundfile,einops.*,av.*,tqdm.*,num2words.*,spacy,xformers.*,scipy,huggingface_hub,transformers,dac.*]
+ignore_missing_imports = True

requirements.txt

@@ -0,0 +1,23 @@
+# please make sure you have already a pytorch install that is cuda enabled!
+av
+einops
+flashy>=0.0.1
+hydra-core>=1.1
+hydra_colorlog
+julius
+num2words
+numpy
+sentencepiece
+spacy>=3.6.1
+torch==2.1.0
+torchaudio>=2.0.0
+huggingface_hub
+tqdm
+transformers>=4.31.0  # need Encodec there.
+xformers
+demucs
+librosa
+gradio
+torchmetrics
+encodec
+protobuf

setup.cfg

@@ -0,0 +1,14 @@
+[pep8]
+max-line-length = 120
+
+[flake8]
+max-line-length = 120
+
+[coverage:report]
+include = audiocraft/*
+omit =
+    audiocraft/environment.py
+    audiocraft/solvers/*
+    audiocraft/utils/*
+    audiocraft/*/loaders.py
+    audiocraft/*/builders.py

setup.py

@@ -0,0 +1,62 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+from pathlib import Path
+
+from setuptools import setup, find_packages
+
+
+NAME = 'audiocraft'
+DESCRIPTION = 'Audio generation research library for PyTorch'
+
+URL = 'https://github.com/facebookresearch/audiocraft'
+AUTHOR = 'FAIR Speech & Audio'
+EMAIL = 'defossez@meta.com, jadecopet@meta.com'
+REQUIRES_PYTHON = '>=3.8.0'
+
+for line in open('audiocraft/__init__.py'):
+    line = line.strip()
+    if '__version__' in line:
+        context = {}
+        exec(line, context)
+        VERSION = context['__version__']
+
+HERE = Path(__file__).parent
+
+try:
+    with open(HERE / "README.md", encoding='utf-8') as f:
+        long_description = '\n' + f.read()
+except FileNotFoundError:
+    long_description = DESCRIPTION
+
+REQUIRED = [i.strip() for i in open(HERE / 'requirements.txt') if not i.startswith('#')]
+
+setup(
+    name=NAME,
+    version=VERSION,
+    description=DESCRIPTION,
+    author_email=EMAIL,
+    long_description=long_description,
+    long_description_content_type='text/markdown',
+    author=AUTHOR,
+    url=URL,
+    python_requires=REQUIRES_PYTHON,
+    install_requires=REQUIRED,
+    extras_require={
+        'dev': ['coverage', 'flake8', 'mypy', 'pdoc3', 'pytest'],
+    },
+    packages=find_packages(),
+    package_data={'audiocraft': ['py.typed']},
+    include_package_data=True,
+    license='MIT License',
+    classifiers=[
+        # Trove classifiers
+        # Full list: https://pypi.python.org/pypi?%3Aaction=list_classifiers
+        'License :: OSI Approved :: MIT License',
+        'Topic :: Multimedia :: Sound/Audio',
+        'Topic :: Scientific/Engineering :: Artificial Intelligence',
+    ],
+)