1

requirements.txt

@@ -1,199 +1,126 @@
-absl-py==2.3.1
+# ============ Core ML / PyTorch ============
+torch==2.6.0
+torchaudio==2.6.0
+torchvision==0.21.0
+lightning==2.6.1
+pytorch-lightning==2.5.5
 accelerate==1.12.0
-aiofiles==24.1.0
-aiohappyeyeballs==2.6.1
-aiohttp==3.12.15
-aiosignal==1.4.0
-alias-free-torch==0.0.6
-annotated-types==0.7.0
-antlr4-python3-runtime==4.9.3
-anyio==4.11.0
-argbind==0.3.9
-argparse==1.4.0
-async-timeout==5.0.1
-attrs==25.3.0
-audiobox-aesthetics==0.0.4
-audioread==3.0.1
-av==16.0.1
-beartype==0.22.2
+transformers==4.57.6
+tokenizers==0.22.2
+safetensors==0.6.2
+peft==0.11.1
 bitsandbytes==0.48.1
-brotli==1.1.0
-certifi==2025.8.3
-cffi==2.0.0
-chardet==5.2.0
-charset-normalizer==3.4.3
-click==8.3.0
-cloudpickle==3.1.1
-colorama==0.4.6
-coloredlogs==15.0.1
-configparser==7.2.0
-cryptography==46.0.3
-datasets==2.21.0
-decorator==5.2.1
-deprecated==1.2.18
 diffusers==0.36.0
-dill==0.3.8
-distro==1.9.0
-dlinfo==2.0.0
-docstring-parser==0.17.0
-easydict==1.13
-einops==0.8.1
-einops-exts==0.0.4
-einx==0.3.0
-ema-pytorch==0.7.7
+datasets==2.21.0
+sentencepiece==0.2.1
+
+# ============ Audio Processing ============
+librosa==0.10.2.post1
+soundfile==0.13.1
+torchcrepe==0.0.24
 encodec==0.1.1
-exceptiongroup==1.3.0
-fastapi==0.118.0
-ffmpy==0.6.1
-filelock==3.19.1
-fire==0.7.1
-flatten-dict==0.4.2
-frozendict==2.4.6
-frozenlist==1.7.0
-fsspec==2024.6.1
-ftfy==6.3.1
-future==1.0.0
-gin-config==0.5.0
-grpcio==1.75.1
-h11==0.16.0
-hf-xet==1.1.10
-httpcore==1.0.9
-httpx==0.28.1
-huggingface-hub==0.35.3
-humanfriendly==10.0
-hydra-core==1.3.2
-idna==3.10
-importlib-metadata==8.7.1
-importlib-resources==6.5.2
-jinja2==3.1.6
-jiter==0.12.0
-joblib==1.5.2
-jsonmerge==1.9.2
-jsonschema==4.25.1
-jsonschema-specifications==2025.9.1
+descript-audio-codec==1.0.0
+descript-audiotools==0.7.2
+vocos==0.1.0
 julius==0.2.7
-k-diffusion==0.1.1
 lameenc==1.8.1
-lazy-loader==0.4
-librosa==0.10.2.post1
-lightning==2.6.1
-lightning-utilities==0.15.2
-llvmlite==0.45.1
-loguru==0.7.3
-loralib==0.1.2
-markdown==3.9
-markdown-it-py==4.0.0
-markdown2==2.5.4
-markupsafe==3.0.3
-mdurl==0.1.2
+pyloudnorm==0.1.1
+pydub==0.25.1
+sox==1.5.0
+soxr==1.0.0
+nnaudio==0.3.3
+av==16.0.1
+audioread==3.0.1
+resampy==0.4.3
+pystoi==0.4.1
+torch-stoi==0.2.3
+torch-complex==0.4.4
+audiobox-aesthetics==0.0.4
+torchcodec==0.10.0
+
+# ============ Music / MIDI ============
+music21==9.9.1
+pretty-midi==0.2.11
 midi2audio==0.1.1
 mido==1.3.3
-ml-collections==1.1.0
+pylrc==0.1.2
+
+# ============ Chinese NLP / TTS ============
+pypinyin==0.55.0
+cn2an==0.5.23
+phonemizer==3.3.0
+jieba==0.42.1
+zhconv==1.4.3
+zhon==2.1.1
+py3langid==0.3.0
+segments==2.3.0
+
+# ============ Model Hubs ============
+huggingface-hub==0.35.3
 modelscope==1.32.0
-more-itertools==10.8.0
-mpmath==1.3.0
-msgpack==1.1.1
-multidict==6.6.4
-multiprocess==0.70.16
-munch==4.0.0
-muq==0.1.0
-music21==9.9.1
-mutagen==1.47.0
-networkx==3.4.2
-nnaudio==0.3.3
-numba==0.62.1
-numpy
+
+# ============ Neural Net Utilities ============
+einops==0.8.1
+einops-exts==0.0.4
+einx==0.3.0
+ema-pytorch==0.7.7
+rotary-embedding-torch==0.8.9
+vector-quantize-pytorch==1.23.2
+x-transformers==2.1.2
+x-clip==0.14.4
+alias-free-torch==0.0.6
+loralib==0.1.2
+k-diffusion==0.1.1
+torchdiffeq==0.2.5
+torchsde==0.2.6
+kornia==0.8.2
+dctorch==0.1.2
+clean-fid==0.1.35
+clip-anytorch==2.6.0
+
+# ============ Config / CLI ============
+hydra-core==1.3.2
 omegaconf==2.3.0
-orjson==3.11.3
-packaging==25.0
-pandas==2.2.3
-peft==0.11.1
-platformdirs==4.4.0
-pooch==1.8.2
+fire==0.7.1
+argbind==0.3.9
 prefigure==0.0.10
-pretty-midi==0.2.11
-propcache==0.3.2
-psutil==7.1.0
-pycparser==2.23
-pydub==0.25.1
-pylance==0.23.2
-pyloudnorm==0.1.1
-pylrc==0.1.2
-pyparsing==3.2.5
-python-dateutil==2.9.0.post0
-python-multipart==0.0.20
-pytorch-lightning==2.5.5
-pytz==2025.2
+gin-config==0.5.0
+ml-collections==1.1.0
+easydict==1.13
 pyyaml==6.0.3
-qwen-omni-utils==0.0.8
-rapidfuzz==2.13.7
-referencing==0.36.2
-regex==2025.9.18
-requests==2.32.5
-resampy==0.4.3
-retrying==1.4.2
-rfc3986==1.5.0
-rich==14.1.0
-rotary-embedding-torch==0.8.9
-rpds-py==0.27.1
-ruamel-yaml==0.19.1
-safetensors==0.6.2
-scikit-learn==1.7.2
-scipy==1.15.3
-segments==2.3.0
-semantic-version==2.10.0
-sentencepiece==0.2.1
-setuptools==80.9.0
-shellingham==1.5.4
-six==1.17.0
-sniffio==1.3.1
-soundfile==0.13.1
-sox==1.5.0
-soxr==1.0.0
-starlette==0.48.0
-sympy==1.13.1
+
+# ============ Web / API (Gradio) ============
+gradio==6.9.0
+
+# ============ Monitoring / Logging ============
+wandb==0.22.1
 tensorboard==2.20.0
-tensorboard-data-server==0.7.2
 tensorboardx==2.6.4
-termcolor==3.1.0
-threadpoolctl==3.6.0
-tokenizers==0.22.2
-tomlkit==0.13.3
-torch==2.6.0
-torch-complex==0.4.4
-torchaudio==2.6.0
-torchcodec==0.10.0
-torchcrepe==0.0.24
-torchdiffeq==0.2.5
-torchmetrics==1.8.2
-torchsde==0.2.6
+loguru==0.7.3
+
+# ============ Data / Science ============
+numpy==2.2.6
+scipy==1.15.3
+pandas==2.2.3
+scikit-learn==1.7.2
+scikit-image==0.25.2
+matplotlib==3.10.8
+pillow==12.1.1
+
+# ============ Misc Utilities ============
 tqdm==4.67.1
-trampoline==0.1.2
-transformers==4.57.6
-triton==3.2.0
-typeguard==4.4.4
-typer==0.19.2
-typing-extensions==4.15.0
-typing-inspection==0.4.2
-tzdata==2025.2
+regex==2025.9.18
+ftfy==6.3.1
 unidecode==1.3.8
-urllib3==2.5.0
-uvicorn==0.37.0
-vector-quantize-pytorch==1.23.2
-vocos==0.1.0
-wandb==0.22.1
-websockets==15.0.1
-wrapt==1.17.3
-x-transformers==2.1.2
-xxhash==3.6.0
-yarl==1.20.1
-zhconv==1.4.3
-zhon==2.1.1
-zipp==3.23.0
-jieba
-pypinyin
-descript-audio-codec
-cn2an
-onnxruntime
-phonemizer
-py3langid
+rapidfuzz==2.13.7
+mutagen==1.47.0
+numba==0.62.1
+onnxruntime==1.23.2
+protobuf==3.19.6
+qwen-omni-utils==0.0.8
+muq==0.1.0
+pylance==0.23.2
+proces==0.1.7
+groovy==0.1.2
+randomname==0.2.1
+submitit==1.5.4