Link the official SAID model repository

README.md

@@ -21,6 +21,8 @@ with a Macro mAP of **0.1080** and a Macro Pearson r of **0.3962**.
 
 Runbang Wang, Zining Liang, Yin Cao, and Qiuqiang Kong
 
+[Pretrained models and Model Card](https://huggingface.co/IN03X/SAID)
+
 ## Overview
 
 ![SAID overview](docs/media/said_overview.png)
@@ -77,8 +79,10 @@ pip install -e .
 
 The paper release contains two complete checkpoints:
 
-- `said_passt.ckpt` for SAID (PaSST), the default model;
-- `said_audiomae.ckpt` for SAID (AudioMAE).
+- [`said_passt.ckpt`](https://huggingface.co/IN03X/SAID/resolve/main/said_passt.ckpt)
+  for SAID (PaSST), the default model;
+- [`said_audiomae.ckpt`](https://huggingface.co/IN03X/SAID/resolve/main/said_audiomae.ckpt)
+  for SAID (AudioMAE).
 
 ### Run the four demos