MERT v1 330M
model·music embedding model·active
Self-supervised acoustic-music representation checkpoint for downstream MIR tasks.
Recorded facts
| Official site | https://huggingface.co/m-a-p/MERT-v1-330M ↗ |
|---|---|
| Geography | unknown |
| parameter count | 330M |
| huggingface repo | m-a-p/MERT-v1-330M |
| api | unknown |
| inputs | 24 kHz music audio |
| license | CC-BY-NC-4.0 |
| outputs | music embeddings at 75 Hz |
| weights | public |
| modalities | 24 kHz music audio; music embeddings at 75 Hz |
| dependencies | unknown |
| model family | MERT |
| access method | downloadable weights; Hugging Face Transformers |
| exact version | MERT-v1-330M |
| repository links | https://huggingface.co/m-a-p/MERT-v1-330M |
| evaluation results | unknown |
| evidence separation | developer claims: · measured results: · independent evaluations: |
| developer maintainer | M-A-P |
| material us relevance | Publicly accessible in or materially offered to the United States market as of snapshot. |
| documented capabilities | music feature extraction; audio classification finetuning |
| products exposing model | unknown |
| commercial use conditions | Model weights are non-commercial under CC-BY-NC-4.0. |
| known geographic or policy restrictions | Non-commercial weights |
| safety watermarking disclosure provenance | unknown |
Current
| introduces (by) | MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training 2023-05-31 — nowSource 1 ↗ VERIFIED high confidence |
|---|---|
| developed (by) | M-A-PSource 1 ↗ PARTY CLAIM medium confidence |
| develops (by) | M-A-PSource 1 ↗ VERIFIED high confidence |
Sources & changes
Checked 11d ago · highhow verification works
Field-level evidence
Public change history
- Status unknown → active
- Official URL unknown → huggingface.co/m-a-p/MERT-v1-330M
- Record maintenance · 12 fields updated
Is this yours? Claim this record →·See something wrong? Report a correction →