unsloth/whisper-large-v3-turbo
Full fine-tune (fewer layers) vs openai/whisper-large-v3. unsloth/whisper-large-v3-turbo matches part of openai/whisper-large-v3 (587 of its 1259 tensors; the rest of openai/whisper-large-v3 has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 2/3, Attention 280/280, Norms 156/156, MLP 144/144, other 4/4
51 other repos hold byte-for-byte identical weight files.