Update README.md


README.md

@@ -6,4 +6,32 @@ base_model:
 - microsoft/Phi-4-multimodal-instruct
 pipeline_tag: audio-text-to-text
 library_name: adapter-transformers
----
+---
+
+# The model for the paper 'StreamUni: Achieving Streaming Speech Translation with a Unified Large Speech-Language Model'
+<div align="center">
+  <a data-pswp-width='1000' data-pswp-height='800' target='_blank' href="https://cdn-uploads.huggingface.co/production/uploads/66680c0505c407bfea87667c/sQXBy7hBmeFYtYbttLuI_.png"><img src="https://cdn-uploads.huggingface.co/production/uploads/66680c0505c407bfea87667c/sQXBy7hBmeFYtYbttLuI_.png" alt="model.png" width="1000"/></a>
+</div>
+
+## Usage
+
+### Requirements
+
+Phi-4 family has been integrated in the `4.48.2` version of `transformers`. The current `transformers` version can be verified with: `pip list | grep transformers`.
+We suggest to run with Python 3.10.
+Examples of required packages:
+```
+flash_attn==2.7.4.post1
+torch==2.6.0
+transformers==4.48.2
+accelerate==1.3.0
+soundfile==0.13.1
+pillow==11.1.0
+scipy==1.15.2
+torchvision==0.21.0
+backoff==2.2.1
+peft==0.13.2
+```
+
+## Training Datasets
+- https://huggingface.co/ICTNLP/StreamUni