ivrit-ai/whisper-large-v3
Full fine-tune vs openai/whisper-large-v3. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 2/3, Attention 672/672, Norms 324/324, MLP 256/256, other 4/4
1 derivatives checked
- mlx-community/ivrit-ai-whisper-large-v3-mlx: Different architecture