moorlee/qwen3-asr-0.6b-hinglish
Full fine-tune vs Qwen/Qwen3-ASR-0.6B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: other 11/11, MLP 156/156, Norms 107/187, Attention 256/256, Embeddings 1/1
Full fine-tune vs Qwen/Qwen3-ASR-0.6B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: other 11/11, MLP 156/156, Norms 107/187, Attention 256/256, Embeddings 1/1