Upload README.md with huggingface_hub

README.md

@@ -1,3 +1,70 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+tags:
+  - music
+  - audio
+  - popularity-prediction
+  - aesthetic-quality
+  - multi-task-learning
+  - mert
+  - ai-generated-music
+  - suno
+  - udio
+language:
+  - en
+library_name: transformers
+---
+
+# APEX: Large-Scale Multi-Task Aesthetic-Informed Popularity Prediction for AI-Generated Music
+
+APEX is the first large-scale multi-task learning framework for jointly predicting **popularity** and **aesthetic quality** of AI-generated music from audio alone. It is trained on over 211k AI-generated songs (~10k hours of audio) from Suno and Udio, leveraging [MERT-v1-95M](https://huggingface.co/m-a-p/MERT-v1-95M) audio embeddings.
+
+---
+
+## What does APEX predict?
+
+Given any audio file, APEX predicts 7 scores:
+
+**Popularity:**
+| Score | Range | Description |
+|---|---|---|
+| `score_streams` | 0–100 | Predicted streaming engagement score |
+| `score_likes` | 0–100 | Predicted likes engagement score |
+
+**Aesthetic Quality (from [SongEval](https://github.com/ASLP-lab/SongEval)):**
+| Score | Range | Description |
+|---|---|---|
+| `coherence` | 1–5 | Structural and harmonic coherence |
+| `musicality` | 1–5 | Overall musical quality |
+| `memorability` | 1–5 | How memorable the song is |
+| `clarity` | 1–5 | Clarity of production and mix |
+| `naturalness` | 1–5 | Naturalness of the generated audio |
+
+---
+
+## Architecture
+
+![APEX Architecture](architecture.png)
+
+---
+
+## Usage
+
+### Installation
+
+```bash
+pip install torch transformers soundfile torchaudio
+```
+
+### Inference
+
+```python
+from transformers import AutoModel
+
+model   = AutoModel.from_pretrained("amaai-lab/apex", trust_remote_code=True)
+results = model.predict("my_song.mp3", save_json="results.json")
+
+print(results["score_streams"])  # popularity score 0-100
+print(results["score_likes"])    # popularity score 0-100
+print(results["coherence"])      # aesthetic score 1-5
+```