diff --git a/README.md b/README.md
index 10ed0d4..c0d8c17 100644
--- a/README.md
+++ b/README.md
@@ -200,6 +200,10 @@ Use any file manager, or a tool like [Label Studio](https://labelstud.io/) for f
 
 ### Step 2 — Auto-label & Review
 
+<div align="center">
+    <video src="assets/video/Auto Label.mp4" title="Auto Label.mp4" width="75%" controls></video>
+</div>
+
 > Use this step once you have a trained classifier. It replaces manual labelling almost entirely.
 
 Runs the full detect → crop → classify pipeline in one command, then opens a browser UI where you review, confirm, fix, or reject each prediction.
@@ -478,7 +482,7 @@ After training, download from `/kaggle/working/runs/classify/`:
 These two files are all you need to run `3_inference.py` and `api_server.py`.
 
    <div align="center">
-      <video src="assets/video/Training Model.mp4" title="Update Dataset.mp4" width="75%" controls></video>
+      <video src="assets/video/Training Model.mp4" title="Training Model.mp4" width="75%" controls></video>
    </div>
 
 #### Option C — Fully automated via `kaggle_train.py`