mesolitica/Malaysian-whisper-large-v3-turbo-v3
Full fine-tune vs openai/whisper-large-v3-turbo. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/2, Norms 133/156, Attention 280/280, MLP 144/144, other 4/4
Full fine-tune vs openai/whisper-large-v3-turbo. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/2, Norms 133/156, Attention 280/280, MLP 144/144, other 4/4