Upload folder using huggingface_hub

README.md

@@ -1,12 +1,33 @@
 ---
-title: Music Recommender
-emoji: 🐢
-colorFrom: indigo
-colorTo: green
+title: AI Music Recommender
+emoji: 🎵
+colorFrom: purple
+colorTo: pink
 sdk: gradio
-sdk_version: 5.49.0
+sdk_version: 4.44.0
 app_file: app.py
 pinned: false
+license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# 🎵 AI Music Recommendation System
+
+An intelligent music recommendation system that combines CNN-based playlist classification with cosine similarity search.
+
+## 🚀 Features
+
+- **Smart Playlist Prediction**: Uses a trained CNN to predict the top 2 most likely playlists for any song
+- **Efficient Search**: Reduces search space by only looking within predicted playlists
+- **Audio Feature Analysis**: Powered by MERT (Music Understanding Model) embeddings
+- **Real-time Recommendations**: Get instant song suggestions based on audio similarity
+
+## 🎯 Technical Stack
+
+- **Model**: Custom 1D CNN for playlist classification
+- **Features**: MERT audio embeddings
+- **Similarity**: Cosine similarity on L2-normalized feature vectors
+- **Search**: K-Nearest Neighbors (KNN) with reduced search space
+
+## 🎓 Academic Project
+
+This is a class project demonstrating the application of deep learning to music information retrieval (MIR).

app.py

@@ -0,0 +1,25 @@
+
+import gradio as gr
+from huggingface_hub import hf_hub_download
+import os
+
+# Download model and cache on startup
+if not os.path.exists("best_model.pth"):
+    print("📥 Downloading model...")
+    hf_hub_download(
+        repo_id="YOUR_USERNAME/music-recommender-assets",
+        filename="best_model.pth",
+        local_dir=".",
+        repo_type="model"
+    )
+
+if not os.path.exists("features_cache.h5"):
+    print("📥 Downloading features...")
+    hf_hub_download(
+        repo_id="YOUR_USERNAME/music-recommender-assets",
+        filename="features_cache.h5",
+        local_dir=".",
+        repo_type="model"
+    )
+
+# ... rest of your app.py code ...

requirements.txt

@@ -0,0 +1,5 @@
+gradio
+torch
+numpy
+scikit-learn
+h5py