Third Party Models
aatmanvaidya
released this
28 Feb 11:59
·
492 commits
to main
since this release
- This release is to upload and all the third party models that
Feluda
uses for its operators.
PANNs inferece
- https://github.com/qiuqiangkong/panns_inference
PANN is a CNN that is pre-trained on lot of audio files. They have been used for audio tagging and sound event detection. The PANNs have been used to fine-tune several audio pattern recognition tasks, and have outperformed several state-of-the-art systems. Feluda uses PANN's to extract a 2048 dimension vector of any given audio file.
Thepth
file of the CNN model will be used in theaudio_vec_embedding
operator.