Update README.md

README.md

@@ -3,8 +3,11 @@ license: apache-2.0
 ---
 # EgoSpeak Checkpoints
 
-This repo hosts checkpoints for all EgoSpeak experiments:
+This repo contains final checkpoints for the EgoSpeak project.  
+- **Models**: `lstr`, `mamba`, `miniroad`  
+- **Datasets**: `easycom`, `ego4dshuffle`, `ytconv_pretrained`  
+- **Modalities**: `A` (audio), `V` (video), `AV` (audio+video)  
+
+## File Naming Convention
+- `mamba_easycom_A.pth` → Mamba model, trained on EasyCom, audio-only
 
-- **Datasets**: EasyCom, Ego4D, Pretrain, Pretrain+EasyCom, Pretrain+Ego4D  
-- **Modalities**: Audio (A), Video (V), Audio+Video (AV)  
-- **Models**: Transformer, GRU, Mamba