1793286693.992 [nemo-speech] transcribe session started
1793286696.370 model has unused tensor blk.52.nextn.enorm.weight (size = 10752 bytes) -- ignoring
1793286696.370 model has unused tensor blk.52.nextn.hnorm.weight (size = 10752 bytes) -- ignoring
1793286696.370 model has unused tensor blk.52.nextn.eh_proj.weight (size = 15353856 bytes) -- ignoring
1793286696.370 model has unused tensor blk.52.nextn.shared_head_norm.weight (size = 10752 bytes) -- ignoring
1793286696.370 model has unused tensor blk.52.attn_norm.weight (size = 10752 bytes) -- ignoring
1793286696.370 model has unused tensor blk.52.attn_q.weight (size = 11698176 bytes) -- ignoring
1793286696.370 model has unused tensor blk.52.attn_k.weight (size = 731136 bytes) -- ignoring
1793286696.370 model has unused tensor blk.52.attn_v.weight (size = 731136 bytes) -- ignoring
1793286696.370 model has unused tensor blk.52.attn_output.weight (size = 11698176 bytes) -- ignoring
1793286696.370 model has unused tensor blk.52.post_attention_norm.weight (size = 10752 bytes) -- ignoring
1793286696.370 model has unused tensor blk.52.ffn_gate_inp.weight (size = 688128 bytes) -- ignoring
1793286696.370 model has unused tensor blk.52.exp_probs_b.bias (size = 512 bytes) -- ignoring
1793286696.370 model has unused tensor blk.52.ffn_down_exps.weight (size = 359202816 bytes) -- ignoring
1793286696.370 model has unused tensor blk.52.ffn_up_exps.weight (size = 359202816 bytes) -- ignoring
1793286696.370 model has unused tensor blk.52.ffn_down_shexp.weight (size = 10601472 bytes) -- ignoring
1793286696.370 model has unused tensor blk.52.ffn_up_shexp.weight (size = 10601472 bytes) -- ignoring
1793286706.105 .............................................................
1793286706.124 [salm] script guard: 37825 of 131072 tokens are not Latin script
1793286706.125 [salm] path=batched (patched ggml, CUDA) mtp_draft=0 slots=1 n_batch=256
1793286715.331 ggml_backend_cuda_buffer_type_alloc_buffer: allocating 219.87 MiB on device 0: cudaMalloc failed: out of memory
1793286715.341 nemo-speech transcribe: /w/audio/librispeech-test-clean-1h.wav: SALM: failed to allocate named-tensor buffer for buffer type CUDA0 (out of device memory?)
1793286715.415 [nemo-speech] transcribe session failed (exit code 1)