diff --git a/README.md b/README.md
index 40e2568..1bb7029 100644
--- a/README.md
+++ b/README.md
@@ -75,7 +75,7 @@ We'd like to thank [PsiPi](https://huggingface.co/PsiPi) for sharing an interest
 
 ```bash
 python demo/gradio_demo.py --model_path vibevoice/VibeVoice-1.5B --share
-# or python demo/gradio_demo.py --model_path vibevoice/VibeVoice-Large --share
+# or python demo/gradio_demo.py --model_path vibevoice/VibeVoice-7B --share
 ```
 
 **Option 2: Inference from files directly**
@@ -83,10 +83,10 @@ python demo/gradio_demo.py --model_path vibevoice/VibeVoice-1.5B --share
 ```bash
 # We provide some LLM generated example scripts under demo/text_examples/ for demo
 # 1 speaker
-python demo/inference_from_file.py --model_path vibevoice/VibeVoice-Large --txt_path demo/text_examples/1p_abs.txt --speaker_names Alice
+python demo/inference_from_file.py --model_path vibevoice/VibeVoice-7B --txt_path demo/text_examples/1p_abs.txt --speaker_names Alice
 
 # or more speakers
-python demo/inference_from_file.py --model_path vibevoice/VibeVoice-Large --txt_path demo/text_examples/2p_music.txt --speaker_names Alice Frank
+python demo/inference_from_file.py --model_path vibevoice/VibeVoice-7B --txt_path demo/text_examples/2p_music.txt --speaker_names Alice Frank
 ```
 
 
@@ -132,4 +132,4 @@ In fact, we intentionally decided not to denoise our training data because we th
 
 The source code and models are licensed under the MIT License. See the [LICENSE](./LICENSE) file for details.
 
-Note: Microsoft has removed the original repo and models. This fork is based off of the MIT-licensed code from Microsoft.
\ No newline at end of file
+Note: Microsoft has removed the original repo and models. This fork is based off of the MIT-licensed code from Microsoft.