ecapa-tdnn-onnx

ONNX export of SpeechBrain's spkrec-ecapa-voxceleb (80-mel fbank input โ†’ 192-dim embedding) used by mellonella.

Format: ONNX (custom mellonella-side export, see scripts/export_*.py in the mellonella repository). Not interchangeable with other community ONNX mirrors โ€” the I/O contract is specific to this project.

Source repository: https://github.com/penta2himajin/mellonella

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support