gcoli/whisper-large-v3-swiss-german-mit
LoRA-style vs openai/whisper-large-v3. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/3, Attention 192/672, Norms 0/324, MLP 0/256, other 0/4