vadimbelsky/qwen3-asr-arabic-uae

Partial fine-tune vs Qwen/Qwen3-ASR-1.7B. Partial change: 84% of the weights changed (attention, embeddings, mlp, norms), in 28 of 28 layers.

Tensors changed: other 0/11, MLP 84/180, Norms 90/211, Attention 112/304, Embeddings 1/1

On the Hub · Downloads on Model Pulse