Apel-sin/whisper-large-v3-russian-ties-podlodka-v1.2

Full fine-tune vs antony66/whisper-large-v3-russian. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/3, Norms 244/324, Attention 672/672, MLP 256/256, other 4/4

On the Hub · Downloads on Model Pulse