matteospanio (Matteo Spanio)

updated a model 1 day ago

csc-unipd/wav2taste

Updated 1 day ago

published a model 1 day ago

csc-unipd/wav2taste

Updated 1 day ago

liked a model 12 days ago

yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF

Text Generation • 12B • Updated 10 days ago • 550k • 2.47k

upvoted a changelog 20 days ago

Hugging Face Changelog

Publish models from CI without HF_TOKEN

20 days ago

• 112

reacted to their post with 🚀 22 days ago

Post

7054

🎶 Released mule-torch — an unofficial PyTorch port of MULE (SF-NFNet-F0), SiriusXM/Pandora's music-audio embedding model (McCallum et al., ISMIR 2022).

No retraining: I re-implemented the architecture in pure PyTorch and transferred the original TensorFlow weights, then checked it layer by layer against the genuine TF pipeline.

✅ End-to-end clip-embedding cosine 0.9999999 vs the original
✅ ONNX backbone parity < 1e-6
✅ 62.35M params (paper: ~62.4M)
✅ Batched, GPU-native, ONNX-exportable — none of which the original Analysis pipeline does

pip install mule-torch

from mule_torch import MuleModel
emb = MuleModel.from_pretrained()(waveform)   # (B, T)@16kHz -> (B, 1728)

🤗 Weights: matteospanio/mule
💻 Code: https://github.com/matteospanio/mule-torch
📦 PyPI: https://pypi.org/project/mule-torch/

The fun bug: parity was perfect through every conv but the block output was anti-correlated (cos = −1). Cause: the learnable skip-init gains couldn't be mapped by layer name (Keras scrambles the order) — they had to be recovered from the graph.

⚠️ Unofficial, community port — not affiliated with or endorsed by the original authors. All credit to them; please cite the paper. Weights inherit CC-BY-NC-4.0.

liked a model 22 days ago

matteospanio/mule

Feature Extraction • 66.6M • Updated 22 days ago • 119 • 3

posted an update 22 days ago

Post

7054

🎶 Released mule-torch — an unofficial PyTorch port of MULE (SF-NFNet-F0), SiriusXM/Pandora's music-audio embedding model (McCallum et al., ISMIR 2022).

No retraining: I re-implemented the architecture in pure PyTorch and transferred the original TensorFlow weights, then checked it layer by layer against the genuine TF pipeline.

✅ End-to-end clip-embedding cosine 0.9999999 vs the original
✅ ONNX backbone parity < 1e-6
✅ 62.35M params (paper: ~62.4M)
✅ Batched, GPU-native, ONNX-exportable — none of which the original Analysis pipeline does

pip install mule-torch

from mule_torch import MuleModel
emb = MuleModel.from_pretrained()(waveform)   # (B, T)@16kHz -> (B, 1728)

🤗 Weights: matteospanio/mule
💻 Code: https://github.com/matteospanio/mule-torch
📦 PyPI: https://pypi.org/project/mule-torch/

The fun bug: parity was perfect through every conv but the block output was anti-correlated (cos = −1). Cause: the learnable skip-init gains couldn't be mapped by layer name (Keras scrambles the order) — they had to be recovered from the graph.

⚠️ Unofficial, community port — not affiliated with or endorsed by the original authors. All credit to them; please cite the paper. Weights inherit CC-BY-NC-4.0.