AI/MLMar 2026 — Present
Melody Retrieval System
Creator
A gamified “sing-to-search” engine: hum a tune, get percentage-scored matches against a MIDI corpus.
- MERT-v1-95M
- Backbone
- FAISS ANN
- Retrieval
- H100
- Trained on
Highlights
- Architecting a semantic music search engine that returns precise percentage-based similarity scores for vocal input against the POP909 MIDI dataset.
- Used a MERT-v1-95M transformer backbone for robust audio embeddings, integrated with FAISS for approximate nearest-neighbor retrieval at scale.
- Fine-tuned a custom MelodyEmbeddingModel on an H100 GPU with triplet loss and hard-negative mining to sharpen embedding separation and retrieval precision.
Stack
PythonMERT-v1-95MFAISSPyTorchHuggingFace