freds0/distil-whisper-large-v3-ptbr

Partial fine-tune vs distil-whisper/distil-large-v3. Partial change: 16% of the weights changed (attention, embeddings, mlp, norms), in 2 of 32 layers.

Tensors changed: Embeddings 2/3, Norms 14/144, Attention 28/252, MLP 8/136, other 0/4

On the Hub · Downloads on Model Pulse