edwixx/omnivoice-brpt-v15
Full fine-tune vs k2-fsa/OmniVoice. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: other 1/2, Embeddings 2/2, Norms 113/113, MLP 84/84, Attention 112/112
Full fine-tune vs k2-fsa/OmniVoice. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: other 1/2, Embeddings 2/2, Norms 113/113, MLP 84/84, Attention 112/112