firdhokk/speech-emotion-recognition-with-openai-whisper-large-v3
Full fine-tune (fewer layers) vs openai/whisper-large-v3. firdhokk/speech-emotion-recognition-with-openai-whisper-large-v3 matches part of openai/whisper-large-v3 (487 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: other 4/4, Embeddings 0/1, Norms 130/130, MLP 128/128, Attention 224/224
2 other repos hold byte-for-byte identical weight files.