artoowang/hf-audio-wav2vec2-bert-CV16-en-finetune

Full fine-tune vs hf-audio/wav2vec2-bert-CV16-en. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: lm_head 2/2, MLP 196/196, Norms 296/296, other 76/76, Attention 202/202, Embeddings 24/24

On the Hub · Downloads on Model Pulse