rev req

requirements.txt

@@ -1,13 +1,27 @@
+# Core dependencies
 torch>=2.0.0
 transformers>=4.34.0
 gradio>=4.13.0
-Pillow>=9.0.0
+
+# Audio processing and model dependencies
+datasets[audio]>=2.14.0
+evaluate>=0.4.0
+jiwer>=3.0.0
+
+# Optimization and acceleration
 bitsandbytes>=0.41.1
 accelerate>=0.24.1
+xformers>=0.0.27
+
+# Hugging Face integration
 huggingface_hub>=0.19.3
 peft
 spaces
-xformers>=0.0.27
-datasets[audio]>=2.14.0
-evaluate>=0.4.0
-jiwer>=3.0.0
+
+# Image processing
+Pillow>=9.0.0
+
+# Additional required packages for whisper model
+librosa
+soundfile
+ffmpeg-python