Update README.md

README.md

@@ -10,6 +10,15 @@ Audio to audio inference doesn't seem good at all. Potentially I am tokenizing t
 
 Script here works with just single speaker - if you know how to get other speakers let me know and I'll update it.
 
+to install requirements for the sample Gradio demo provided, please run:
+
+```
+pip install torch torchaudio --index-url https://download.pytorch.org/whl/cu121
+pip install gradio tempfile transformers numpy
+```
+
+Remember that you also need to install the [spiritlm](https://github.com/facebookresearch/spiritlm) module.
+
 ```python
 import gradio as gr
 from spiritlm.model.spiritlm_model import Spiritlm, OutputModality, GenerationInput, ContentType