diffuserfix

requirements.txt

@@ -1,34 +1,47 @@
+# Core PyTorch dependencies
 torch==2.0.1
 torchaudio==2.0.2
 torchvision==0.15.2
+
+# Hugging Face ecosystem - aligned versions
 transformers==4.27.0
 accelerate==0.21.0
+diffusers==0.19.3
+huggingface_hub>=0.23.4  # Updated to satisfy bigvgan requirement
 datasets==2.1.0
+safetensors==0.3.2
+
+# Audio processing
+librosa==0.9.2
+soundfile==0.12.1
+torchlibrosa==0.1.0
+wavio==0.0.7
+resampy==0.4.2
+ssr_eval==0.0.6
+bigvgan==2.4.1
+
+# Data processing and visualization
+numpy==1.23.0
+pandas==1.4.1
+matplotlib==3.5.2
+scikit_image==0.19.3
+scikit_learn==1.2.2
+scipy==1.8.0
+
+# Utils and others
 einops==0.6.1
 h5py==3.8.0
-diffusers==0.19.3  # Version compatible with older huggingface_hub
-huggingface_hub==0.16.4 
 importlib_metadata==6.3.0
-librosa==0.9.2
-matplotlib==3.5.2
-numpy==1.23.0
 omegaconf==2.3.0
 packaging==23.1
-pandas==1.4.1
 progressbar33==2.4
-protobuf==3.20.*
-resampy==0.4.2
-safetensors==0.3.2
+protobuf==3.20.3
 sentencepiece==0.1.99
-scikit_image==0.19.3
-scikit_learn==1.2.2
-scipy==1.8.0
-soundfile==0.12.1
-ssr_eval==0.0.6
-torchlibrosa==0.1.0
 tqdm==4.63.1
 wandb==0.12.14
 ipython==8.12.0
-gradio==4.3.0
-wavio==0.0.7
-bigvgan==2.4.1
+gradio>=4.3.0  # Allow newer versions for compatibility
+
+# Dependencies needed by audio processing
+ffmpeg-python
+ninja