MattyB95/AST-ASVspoof2019-Synthetic-Voice-Detection
Full fine-tune vs MIT/ast-finetuned-audioset-10-10-0.4593. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 5/5, Attention 96/96, other 48/48, Norms 52/52
Full fine-tune vs MIT/ast-finetuned-audioset-10-10-0.4593. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 5/5, Attention 96/96, other 48/48, Norms 52/52