Downloads · 30 days
5
38% of all-time downloads
dasheng-mae-decoder-audioset24k
quinnlue/dasheng-mae-decoder-audioset24k
dasheng-mae-decoder-audioset24k is a machine learning model from quinnlue. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Frozen dasheng-base encoder with a trained MAE decoder (8-layer, d=512), trained for one epoch on danjacobellis/audiosetopus24kbps to reconstruct masked mel patches (mask ratio 0.75, group factor 2).
All-time downloads
13
Public
Repo size
653 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt653 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jun 17, 2026
- Updated
- Jun 17, 2026
- SHA
- 393344ef
Model card
From the Hugging Face model README
dasheng-base + MAE decoder (AudioSet-Opus 24kbps)
Frozen dasheng-base encoder with a trained MAE decoder (8-layer, d=512), trained for one epoch on danjacobellis/audioset_opus_24kbps to reconstruct masked mel patches (mask ratio 0.75, group factor 2).
The encoder was never updated. This checkpoint is used for hard-example mining: per-clip reconstruction loss is the difficulty signal for SSL data curation.
last.pt / best.pt are PyTorch payloads with model_state (encoder) and
objective_state (encoder + decoder). config.json is the full training config.
- License
- apache-2.0
- Created
- Jun 17, 2026
- Updated
- Jun 17, 2026