Update README.md

README.md

@@ -24,14 +24,20 @@ This is a LoRA (Low-Rank Adaptation) fine-tuned model for Arabic text-to-speech,
 
 - **Base Model**: [aoi-ot/VibeVoice-Large](https://huggingface.co/aoi-ot/VibeVoice-Large)
 - **Training Method**: LoRA fine-tuning
-- **Language**: Arabic (with English support retained)
+- **Language**: Arabic 
 - **License**: MIT
 
 ## Requirements
 
 ### Hardware
-- **Inference**: 16GB+ VRAM recommended
+- **Inference**:
+  - VibeVoice-1.5B: 8GB+ VRAM
+  - VibeVoice-Large (7B): 16GB+ VRAM
 - **Training**: 48GB+ VRAM for VibeVoice-Large
+  - VibeVoice-1.5B LoRA: 16GB+ VRAM minimum
+  - VibeVoice-Large (7B) LoRA: 48GB+ VRAM minimum
+
+
 
 ### Software
 ```bash