Add pyproject.toml, loosen dependencies

pyproject.toml

@@ -1,3 +1,55 @@
 [build-system]
-requires = ["setuptools"]
-build-backend = "setuptools.build_meta"
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "stable-audio-tools"
+version = "0.0.20"
+authors = [
+    {name = "Stability AI"}
+]
+description = "Training and inference tools for generative audio models from Stability AI"
+readme = "README.md"
+requires-python = ">=3.8"
+license = {file = "LICENSE"}
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
+]
+dependencies = [
+    "alias-free-torch>=0.0.6",
+    "auraloss>=0.4.0",
+    "descript-audio-codec>=1.0.0",
+    "einops",
+    "einops-exts",
+    "ema-pytorch>=0.2.3",
+    "encodec>=0.1.1",
+    "gradio>=5.20.0",
+    "huggingface_hub",
+    "importlib-resources>=5.12.0",
+    "k-diffusion>=0.1.1",
+    "laion-clap>=1.1.4",
+    "local-attention>=1.8.6",
+    "pandas>=2.2.0",
+    "prefigure>=0.0.10",
+    "pytorch_lightning>=2.5.1",
+    "PyWavelets>=1.8.0",
+    "safetensors>=0.5.0",
+    "sentencepiece>=0.2.0",
+    "torch>=2.5.0",
+    "torchaudio>=2.5.0",
+    "torchmetrics>=1.7.0",
+    "tqdm",
+    "transformers>=4.51.3",
+    "v-diffusion-pytorch>=0.0.2",
+    "vector-quantize-pytorch>=1.22.0",
+    "wandb>=0.19.0",
+    "webdataset>=0.2.100"
+]
+
+[project.urls]
+"Homepage" = "https://github.com/Stability-AI/stable-audio-tools"
+"Bug Tracker" = "https://github.com/Stability-AI/stable-audio-tools/issues"
+
+[tool.setuptools.packages.find]
+include = ["stable_audio_tools*"]

setup.py

@@ -2,39 +2,39 @@
 
 setup(
     name='stable-audio-tools',
-    version='0.0.19',
+    version='0.0.20',
     url='https://github.com/Stability-AI/stable-audio-tools.git',
     author='Stability AI',
     description='Training and inference tools for generative audio models from Stability AI',
     packages=find_packages(),  
     install_requires=[
-        'alias-free-torch==0.0.6',
-        'auraloss==0.4.0',
-        'descript-audio-codec==1.0.0',
-        'einops',
-        'einops-exts',
-        'ema-pytorch==0.2.3',
-        'encodec==0.1.1',
-        'gradio>=5.20.0',
-        'huggingface_hub',
-        'importlib-resources==5.12.0',
-        'k-diffusion==0.1.1',
-        'laion-clap==1.1.4',
-        'local-attention==1.8.6',
-        'pandas==2.0.2',
-        'prefigure==0.0.9',
-        'pytorch_lightning==2.1.0',
-        'PyWavelets==1.4.1',
-        'safetensors',
-        'sentencepiece==0.1.99',
-        'torch>=2.5.1',
-        'torchaudio>=2.5.1',
-        'torchmetrics==0.11.4',
-        'tqdm',
-        'transformers',
-        'v-diffusion-pytorch==0.0.2',
-        'vector-quantize-pytorch==1.14.41',
-        'wandb==0.15.4',
-        'webdataset==0.2.100'
+        "alias-free-torch>=0.0.6",
+        "auraloss>=0.4.0",
+        "descript-audio-codec>=1.0.0",
+        "einops",
+        "einops-exts",
+        "ema-pytorch>=0.2.3",
+        "encodec>=0.1.1",
+        "gradio>=5.20.0",
+        "huggingface_hub",
+        "importlib-resources>=5.12.0",
+        "k-diffusion>=0.1.1",
+        "laion-clap>=1.1.4",
+        "local-attention>=1.8.6",
+        "pandas>=2.2.0",
+        "prefigure>=0.0.10",
+        "pytorch_lightning>=2.5.1",
+        "PyWavelets>=1.8.0",
+        "safetensors>=0.5.0",
+        "sentencepiece>=0.2.0",
+        "torch>=2.5.0",
+        "torchaudio>=2.5.0",
+        "torchmetrics>=1.7.0",
+        "tqdm",
+        "transformers>=4.51.3",
+        "v-diffusion-pytorch>=0.0.2",
+        "vector-quantize-pytorch>=1.22.0",
+        "wandb>=0.19.0",
+        "webdataset>=0.2.100"
     ],
 )