NbAiLab/nb-whisper-tiny

Full fine-tune vs openai/whisper-tiny. Fine-tune: 100% of the weights changed, across 4 of 4 layers.

Tensors changed: Embeddings 3/3, Norms 44/44, Attention 84/84, MLP 32/32, other 4/4

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse