inference/log1.txt

[2025-09-15 09:26:52,568] [INFO] [real_accelerator.py:222:get_accelerator] Setting ds_accelerator to cuda (auto detect)
LOAD_VISION_EARLY is set
FORCE_NO_DOWNSAMPLE is set
VIDEO_RESIZE is set as 0x64, 0, 64
HIGHRES_BASE is set as 0x32, 0, 32
MAXRES is set as 1536
MINRES is set as 0
VIDEO_MAXRES is set as 480
VIDEO_MINRES is set as 288
PAD2STRIDE is set
LOWRES_RESIZE is set as 384x32
Loading OlaQwen3ForCausalLM model...
Loading BEATs Model
Missing keys: ['model.speech_encoder.whisper_model.positional_embedding', 'model.speech_encoder.whisper_model.conv1.weight', 'model.speech_encoder.whisper_model.conv1.bias', 'model.speech_encoder.whisper_model.conv2.weight', 'model.speech_encoder.whisper_model.conv2.bias', 'model.speech_encoder.whisper_model.blocks.0.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.0.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.0.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.0.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.0.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.0.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.0.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.0.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.0.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.0.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.0.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.0.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.0.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.0.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.0.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.1.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.1.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.1.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.1.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.1.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.1.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.1.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.1.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.1.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.1.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.1.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.1.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.1.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.1.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.1.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.2.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.2.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.2.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.2.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.2.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.2.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.2.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.2.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.2.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.2.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.2.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.2.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.2.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.2.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.2.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.3.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.3.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.3.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.3.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.3.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.3.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.3.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.3.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.3.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.3.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.3.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.3.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.3.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.3.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.3.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.4.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.4.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.4.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.4.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.4.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.4.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.4.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.4.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.4.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.4.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.4.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.4.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.4.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.4.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.4.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.5.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.5.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.5.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.5.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.5.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.5.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.5.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.5.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.5.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.5.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.5.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.5.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.5.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.5.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.5.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.6.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.6.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.6.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.6.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.6.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.6.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.6.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.6.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.6.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.6.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.6.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.6.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.6.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.6.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.6.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.7.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.7.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.7.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.7.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.7.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.7.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.7.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.7.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.7.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.7.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.7.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.7.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.7.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.7.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.7.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.8.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.8.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.8.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.8.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.8.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.8.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.8.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.8.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.8.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.8.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.8.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.8.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.8.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.8.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.8.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.9.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.9.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.9.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.9.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.9.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.9.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.9.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.9.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.9.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.9.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.9.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.9.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.9.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.9.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.9.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.10.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.10.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.10.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.10.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.10.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.10.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.10.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.10.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.10.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.10.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.10.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.10.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.10.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.10.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.10.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.11.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.11.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.11.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.11.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.11.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.11.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.11.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.11.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.11.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.11.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.11.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.11.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.11.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.11.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.11.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.12.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.12.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.12.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.12.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.12.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.12.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.12.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.12.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.12.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.12.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.12.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.12.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.12.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.12.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.12.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.13.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.13.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.13.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.13.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.13.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.13.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.13.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.13.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.13.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.13.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.13.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.13.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.13.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.13.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.13.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.14.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.14.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.14.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.14.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.14.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.14.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.14.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.14.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.14.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.14.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.14.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.14.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.14.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.14.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.14.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.15.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.15.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.15.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.15.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.15.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.15.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.15.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.15.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.15.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.15.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.15.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.15.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.15.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.15.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.15.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.16.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.16.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.16.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.16.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.16.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.16.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.16.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.16.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.16.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.16.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.16.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.16.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.16.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.16.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.16.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.17.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.17.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.17.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.17.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.17.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.17.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.17.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.17.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.17.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.17.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.17.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.17.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.17.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.17.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.17.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.18.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.18.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.18.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.18.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.18.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.18.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.18.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.18.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.18.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.18.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.18.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.18.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.18.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.18.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.18.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.19.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.19.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.19.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.19.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.19.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.19.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.19.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.19.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.19.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.19.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.19.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.19.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.19.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.19.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.19.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.20.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.20.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.20.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.20.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.20.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.20.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.20.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.20.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.20.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.20.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.20.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.20.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.20.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.20.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.20.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.21.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.21.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.21.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.21.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.21.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.21.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.21.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.21.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.21.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.21.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.21.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.21.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.21.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.21.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.21.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.22.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.22.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.22.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.22.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.22.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.22.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.22.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.22.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.22.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.22.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.22.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.22.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.22.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.22.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.22.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.23.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.23.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.23.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.23.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.23.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.23.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.23.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.23.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.23.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.23.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.23.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.23.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.23.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.23.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.23.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.24.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.24.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.24.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.24.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.24.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.24.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.24.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.24.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.24.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.24.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.24.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.24.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.24.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.24.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.24.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.25.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.25.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.25.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.25.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.25.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.25.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.25.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.25.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.25.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.25.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.25.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.25.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.25.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.25.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.25.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.26.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.26.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.26.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.26.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.26.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.26.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.26.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.26.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.26.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.26.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.26.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.26.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.26.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.26.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.26.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.27.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.27.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.27.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.27.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.27.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.27.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.27.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.27.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.27.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.27.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.27.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.27.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.27.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.27.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.27.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.28.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.28.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.28.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.28.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.28.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.28.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.28.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.28.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.28.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.28.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.28.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.28.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.28.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.28.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.28.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.29.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.29.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.29.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.29.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.29.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.29.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.29.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.29.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.29.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.29.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.29.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.29.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.29.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.29.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.29.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.30.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.30.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.30.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.30.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.30.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.30.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.30.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.30.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.30.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.30.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.30.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.30.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.30.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.30.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.30.mlp_ln.bias', 'model.speech_encoder.whisper_model.blocks.31.attn.query.weight', 'model.speech_encoder.whisper_model.blocks.31.attn.query.bias', 'model.speech_encoder.whisper_model.blocks.31.attn.key.weight', 'model.speech_encoder.whisper_model.blocks.31.attn.value.weight', 'model.speech_encoder.whisper_model.blocks.31.attn.value.bias', 'model.speech_encoder.whisper_model.blocks.31.attn.out.weight', 'model.speech_encoder.whisper_model.blocks.31.attn.out.bias', 'model.speech_encoder.whisper_model.blocks.31.attn_ln.weight', 'model.speech_encoder.whisper_model.blocks.31.attn_ln.bias', 'model.speech_encoder.whisper_model.blocks.31.mlp.0.weight', 'model.speech_encoder.whisper_model.blocks.31.mlp.0.bias', 'model.speech_encoder.whisper_model.blocks.31.mlp.2.weight', 'model.speech_encoder.whisper_model.blocks.31.mlp.2.bias', 'model.speech_encoder.whisper_model.blocks.31.mlp_ln.weight', 'model.speech_encoder.whisper_model.blocks.31.mlp_ln.bias', 'model.speech_encoder.whisper_model.ln_post.weight', 'model.speech_encoder.whisper_model.ln_post.bias', 'model.speech_encoder.beats_model.post_extract_proj.weight', 'model.speech_encoder.beats_model.post_extract_proj.bias', 'model.speech_encoder.beats_model.patch_embedding.weight', 'model.speech_encoder.beats_model.encoder.pos_conv.0.bias', 'model.speech_encoder.beats_model.encoder.pos_conv.0.weight_g', 'model.speech_encoder.beats_model.encoder.pos_conv.0.weight_v', 'model.speech_encoder.beats_model.encoder.layers.0.self_attn.grep_a', 'model.speech_encoder.beats_model.encoder.layers.0.self_attn.relative_attention_bias.weight', 'model.speech_encoder.beats_model.encoder.layers.0.self_attn.k_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.0.self_attn.k_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.0.self_attn.v_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.0.self_attn.v_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.0.self_attn.q_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.0.self_attn.q_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.0.self_attn.out_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.0.self_attn.out_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.0.self_attn.grep_linear.weight', 'model.speech_encoder.beats_model.encoder.layers.0.self_attn.grep_linear.bias', 'model.speech_encoder.beats_model.encoder.layers.0.self_attn_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.0.self_attn_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.0.fc1.weight', 'model.speech_encoder.beats_model.encoder.layers.0.fc1.bias', 'model.speech_encoder.beats_model.encoder.layers.0.fc2.weight', 'model.speech_encoder.beats_model.encoder.layers.0.fc2.bias', 'model.speech_encoder.beats_model.encoder.layers.0.final_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.0.final_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.1.self_attn.grep_a', 'model.speech_encoder.beats_model.encoder.layers.1.self_attn.k_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.1.self_attn.k_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.1.self_attn.v_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.1.self_attn.v_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.1.self_attn.q_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.1.self_attn.q_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.1.self_attn.out_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.1.self_attn.out_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.1.self_attn.grep_linear.weight', 'model.speech_encoder.beats_model.encoder.layers.1.self_attn.grep_linear.bias', 'model.speech_encoder.beats_model.encoder.layers.1.self_attn.relative_attention_bias.weight', 'model.speech_encoder.beats_model.encoder.layers.1.self_attn_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.1.self_attn_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.1.fc1.weight', 'model.speech_encoder.beats_model.encoder.layers.1.fc1.bias', 'model.speech_encoder.beats_model.encoder.layers.1.fc2.weight', 'model.speech_encoder.beats_model.encoder.layers.1.fc2.bias', 'model.speech_encoder.beats_model.encoder.layers.1.final_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.1.final_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.2.self_attn.grep_a', 'model.speech_encoder.beats_model.encoder.layers.2.self_attn.k_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.2.self_attn.k_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.2.self_attn.v_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.2.self_attn.v_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.2.self_attn.q_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.2.self_attn.q_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.2.self_attn.out_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.2.self_attn.out_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.2.self_attn.grep_linear.weight', 'model.speech_encoder.beats_model.encoder.layers.2.self_attn.grep_linear.bias', 'model.speech_encoder.beats_model.encoder.layers.2.self_attn.relative_attention_bias.weight', 'model.speech_encoder.beats_model.encoder.layers.2.self_attn_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.2.self_attn_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.2.fc1.weight', 'model.speech_encoder.beats_model.encoder.layers.2.fc1.bias', 'model.speech_encoder.beats_model.encoder.layers.2.fc2.weight', 'model.speech_encoder.beats_model.encoder.layers.2.fc2.bias', 'model.speech_encoder.beats_model.encoder.layers.2.final_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.2.final_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.3.self_attn.grep_a', 'model.speech_encoder.beats_model.encoder.layers.3.self_attn.k_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.3.self_attn.k_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.3.self_attn.v_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.3.self_attn.v_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.3.self_attn.q_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.3.self_attn.q_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.3.self_attn.out_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.3.self_attn.out_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.3.self_attn.grep_linear.weight', 'model.speech_encoder.beats_model.encoder.layers.3.self_attn.grep_linear.bias', 'model.speech_encoder.beats_model.encoder.layers.3.self_attn.relative_attention_bias.weight', 'model.speech_encoder.beats_model.encoder.layers.3.self_attn_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.3.self_attn_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.3.fc1.weight', 'model.speech_encoder.beats_model.encoder.layers.3.fc1.bias', 'model.speech_encoder.beats_model.encoder.layers.3.fc2.weight', 'model.speech_encoder.beats_model.encoder.layers.3.fc2.bias', 'model.speech_encoder.beats_model.encoder.layers.3.final_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.3.final_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.4.self_attn.grep_a', 'model.speech_encoder.beats_model.encoder.layers.4.self_attn.k_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.4.self_attn.k_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.4.self_attn.v_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.4.self_attn.v_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.4.self_attn.q_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.4.self_attn.q_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.4.self_attn.out_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.4.self_attn.out_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.4.self_attn.grep_linear.weight', 'model.speech_encoder.beats_model.encoder.layers.4.self_attn.grep_linear.bias', 'model.speech_encoder.beats_model.encoder.layers.4.self_attn.relative_attention_bias.weight', 'model.speech_encoder.beats_model.encoder.layers.4.self_attn_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.4.self_attn_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.4.fc1.weight', 'model.speech_encoder.beats_model.encoder.layers.4.fc1.bias', 'model.speech_encoder.beats_model.encoder.layers.4.fc2.weight', 'model.speech_encoder.beats_model.encoder.layers.4.fc2.bias', 'model.speech_encoder.beats_model.encoder.layers.4.final_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.4.final_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.5.self_attn.grep_a', 'model.speech_encoder.beats_model.encoder.layers.5.self_attn.k_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.5.self_attn.k_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.5.self_attn.v_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.5.self_attn.v_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.5.self_attn.q_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.5.self_attn.q_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.5.self_attn.out_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.5.self_attn.out_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.5.self_attn.grep_linear.weight', 'model.speech_encoder.beats_model.encoder.layers.5.self_attn.grep_linear.bias', 'model.speech_encoder.beats_model.encoder.layers.5.self_attn.relative_attention_bias.weight', 'model.speech_encoder.beats_model.encoder.layers.5.self_attn_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.5.self_attn_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.5.fc1.weight', 'model.speech_encoder.beats_model.encoder.layers.5.fc1.bias', 'model.speech_encoder.beats_model.encoder.layers.5.fc2.weight', 'model.speech_encoder.beats_model.encoder.layers.5.fc2.bias', 'model.speech_encoder.beats_model.encoder.layers.5.final_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.5.final_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.6.self_attn.grep_a', 'model.speech_encoder.beats_model.encoder.layers.6.self_attn.k_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.6.self_attn.k_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.6.self_attn.v_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.6.self_attn.v_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.6.self_attn.q_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.6.self_attn.q_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.6.self_attn.out_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.6.self_attn.out_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.6.self_attn.grep_linear.weight', 'model.speech_encoder.beats_model.encoder.layers.6.self_attn.grep_linear.bias', 'model.speech_encoder.beats_model.encoder.layers.6.self_attn.relative_attention_bias.weight', 'model.speech_encoder.beats_model.encoder.layers.6.self_attn_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.6.self_attn_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.6.fc1.weight', 'model.speech_encoder.beats_model.encoder.layers.6.fc1.bias', 'model.speech_encoder.beats_model.encoder.layers.6.fc2.weight', 'model.speech_encoder.beats_model.encoder.layers.6.fc2.bias', 'model.speech_encoder.beats_model.encoder.layers.6.final_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.6.final_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.7.self_attn.grep_a', 'model.speech_encoder.beats_model.encoder.layers.7.self_attn.k_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.7.self_attn.k_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.7.self_attn.v_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.7.self_attn.v_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.7.self_attn.q_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.7.self_attn.q_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.7.self_attn.out_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.7.self_attn.out_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.7.self_attn.grep_linear.weight', 'model.speech_encoder.beats_model.encoder.layers.7.self_attn.grep_linear.bias', 'model.speech_encoder.beats_model.encoder.layers.7.self_attn.relative_attention_bias.weight', 'model.speech_encoder.beats_model.encoder.layers.7.self_attn_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.7.self_attn_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.7.fc1.weight', 'model.speech_encoder.beats_model.encoder.layers.7.fc1.bias', 'model.speech_encoder.beats_model.encoder.layers.7.fc2.weight', 'model.speech_encoder.beats_model.encoder.layers.7.fc2.bias', 'model.speech_encoder.beats_model.encoder.layers.7.final_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.7.final_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.8.self_attn.grep_a', 'model.speech_encoder.beats_model.encoder.layers.8.self_attn.k_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.8.self_attn.k_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.8.self_attn.v_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.8.self_attn.v_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.8.self_attn.q_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.8.self_attn.q_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.8.self_attn.out_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.8.self_attn.out_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.8.self_attn.grep_linear.weight', 'model.speech_encoder.beats_model.encoder.layers.8.self_attn.grep_linear.bias', 'model.speech_encoder.beats_model.encoder.layers.8.self_attn.relative_attention_bias.weight', 'model.speech_encoder.beats_model.encoder.layers.8.self_attn_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.8.self_attn_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.8.fc1.weight', 'model.speech_encoder.beats_model.encoder.layers.8.fc1.bias', 'model.speech_encoder.beats_model.encoder.layers.8.fc2.weight', 'model.speech_encoder.beats_model.encoder.layers.8.fc2.bias', 'model.speech_encoder.beats_model.encoder.layers.8.final_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.8.final_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.9.self_attn.grep_a', 'model.speech_encoder.beats_model.encoder.layers.9.self_attn.k_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.9.self_attn.k_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.9.self_attn.v_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.9.self_attn.v_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.9.self_attn.q_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.9.self_attn.q_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.9.self_attn.out_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.9.self_attn.out_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.9.self_attn.grep_linear.weight', 'model.speech_encoder.beats_model.encoder.layers.9.self_attn.grep_linear.bias', 'model.speech_encoder.beats_model.encoder.layers.9.self_attn.relative_attention_bias.weight', 'model.speech_encoder.beats_model.encoder.layers.9.self_attn_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.9.self_attn_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.9.fc1.weight', 'model.speech_encoder.beats_model.encoder.layers.9.fc1.bias', 'model.speech_encoder.beats_model.encoder.layers.9.fc2.weight', 'model.speech_encoder.beats_model.encoder.layers.9.fc2.bias', 'model.speech_encoder.beats_model.encoder.layers.9.final_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.9.final_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.10.self_attn.grep_a', 'model.speech_encoder.beats_model.encoder.layers.10.self_attn.k_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.10.self_attn.k_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.10.self_attn.v_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.10.self_attn.v_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.10.self_attn.q_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.10.self_attn.q_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.10.self_attn.out_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.10.self_attn.out_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.10.self_attn.grep_linear.weight', 'model.speech_encoder.beats_model.encoder.layers.10.self_attn.grep_linear.bias', 'model.speech_encoder.beats_model.encoder.layers.10.self_attn.relative_attention_bias.weight', 'model.speech_encoder.beats_model.encoder.layers.10.self_attn_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.10.self_attn_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.10.fc1.weight', 'model.speech_encoder.beats_model.encoder.layers.10.fc1.bias', 'model.speech_encoder.beats_model.encoder.layers.10.fc2.weight', 'model.speech_encoder.beats_model.encoder.layers.10.fc2.bias', 'model.speech_encoder.beats_model.encoder.layers.10.final_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.10.final_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.11.self_attn.grep_a', 'model.speech_encoder.beats_model.encoder.layers.11.self_attn.k_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.11.self_attn.k_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.11.self_attn.v_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.11.self_attn.v_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.11.self_attn.q_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.11.self_attn.q_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.11.self_attn.out_proj.weight', 'model.speech_encoder.beats_model.encoder.layers.11.self_attn.out_proj.bias', 'model.speech_encoder.beats_model.encoder.layers.11.self_attn.grep_linear.weight', 'model.speech_encoder.beats_model.encoder.layers.11.self_attn.grep_linear.bias', 'model.speech_encoder.beats_model.encoder.layers.11.self_attn.relative_attention_bias.weight', 'model.speech_encoder.beats_model.encoder.layers.11.self_attn_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.11.self_attn_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layers.11.fc1.weight', 'model.speech_encoder.beats_model.encoder.layers.11.fc1.bias', 'model.speech_encoder.beats_model.encoder.layers.11.fc2.weight', 'model.speech_encoder.beats_model.encoder.layers.11.fc2.bias', 'model.speech_encoder.beats_model.encoder.layers.11.final_layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layers.11.final_layer_norm.bias', 'model.speech_encoder.beats_model.encoder.layer_norm.weight', 'model.speech_encoder.beats_model.encoder.layer_norm.bias', 'model.speech_encoder.beats_model.layer_norm.weight', 'model.speech_encoder.beats_model.layer_norm.bias', 'model.speech_encoder.beats_model.predictor.weight', 'model.speech_encoder.beats_model.predictor.bias', 'model.speech_projector.speech_newline', 'model.speech_projector.speech_begin', 'model.speech_projector.speech_end', 'model.speech_projector.linear1.weight', 'model.speech_projector.linear1.bias', 'model.speech_projector.linear2.weight', 'model.speech_projector.linear2.bias']
Unexpected keys: []
Loading vision tower...
Loading vision tower succeeded.
User: Hello, who are you?
Assistant: Hello! I am an AI assistant called PLM-V. How can I help you today?

================================================================================
🧪 开始多模态推理测试
================================================================================

============================================================
🧪 测试: Pure Text
📝 问题: Hello, who are you? Please introduce yourself briefly.
============================================================
<|im_start|>system
You are PLM-V, a helpful assistant.<|im_end|>
<|im_start|>user
Hello, who are you? Please introduce yourself briefly.<|im_end|>
<|im_start|>assistant
 Hello! I am PLM-V, a language model created by the platform OpenAI. My primary function is to assist users by providing information, answering questions, and engaging in conversation. I aim to be helpful, accurate, and respectful in all interactions. How can I assist you today?
✅ 推理成功!
🤖 回复: Hello! I am PLM-V, a language model created by the platform OpenAI. My primary function is to assist users by providing information, answering questions, and engaging in conversation. I aim to be helpful, accurate, and respectful in all interactions. How can I assist you today?

============================================================
🧪 测试: Text & Image (Visual only)
📝 问题: <image>
Please describe this image in detail.
============================================================
dynamic ViT batch size: 13
<|im_start|>system
You are PLM-V, a helpful assistant.<|im_end|>
<|im_start|>user
<image>
Please describe this image in detail.<|im_end|>
<|im_start|>assistant
 The image shows a cute red panda sitting on a wooden platform. This reddish-brown animal has distinctive black and white markings: a white face with black stripes on its cheeks and around its nose. Its fur appears soft and fluffy. The red panda has large, dark eyes and white whiskers, adding to its endearing appearance. It is resting close to a tree trunk, with its black ears perked up on either side. The background is filled with blurred green foliage, suggesting this red panda is in a natural or outdoor setting, possibly a zoo or wildlife sanctuary. The wooden platform appears to be part of a structure designed for the animal to rest or climb on comfortably.
✅ 推理成功!
🤖 回复: The image shows a cute red panda sitting on a wooden platform. This reddish-brown animal has distinctive black and white markings: a white face with black stripes on its cheeks and around its nose. Its fur appears soft and fluffy. The red panda has large, dark eyes and white whiskers, adding to its endearing appearance. It is resting close to a tree trunk, with its black ears perked up on either side. The background is filled with blurred green foliage, suggesting this red panda is in a natural or outdoor setting, possibly a zoo or wildlife sanctuary. The wooden platform appears to be part of a structure designed for the animal to rest or climb on comfortably.

============================================================
🔄 准备Speech相关测试 (可能输出乱码，因为speech部分未训练)
============================================================

📥 加载视频数据...
✅ 视频加载成功:
  - 视频帧数: 8
  - 视频像素值形状: torch.Size([8, 3, 448, 448])
  - 每帧patch数: [1, 1, 1, 1, 1, 1, 1, 1]

📥 加载音频数据...
✅ 音频加载成功:
  - mel谱图形状: torch.Size([2, 3000, 128])
  - 音频长度: tensor([3000, 3000])
  - 音频块数: tensor([2])
  - 原始音频波形形状: torch.Size([2, 480000])

============================================================
🧪 测试: Audio only (预期乱码)
📝 问题: <speech>
Please transcribe and summarize what you heard in the audio.
============================================================
speech batch size: 2
<|im_start|>system
You are PLM-V, a helpful assistant.<|im_end|>
<|im_start|>user
<speech>
Please transcribe and summarize what you heard in the audio.<|im_end|>
<|im_start|>assistant
 The秘密 is currently notPowered should be valid.

It's possible that's a complex combination of unsub,$

Here's an unexpected task is to assess the����是有效的。

Now, the秘密

### 払下秘密是从加密的

Here的秘密

It seems the encrypted message has been truncated. It's a confusing combination of unworking! We're not seeing the message from a valid IP的操作未完成. We're here to assist."

It's a sequence of 10.21.48. Here we can assist to encrypting the message. This is the result of a combination of unworking. If you're trying to determine the message that the code for the current message. It seems we're not seeing the message that the network can't work. We're too broad. 

Therefore, the final answer is that we can't help you. We're currently working to inform you. We're now able to help you. 

What did you saw?"

It seems like the message is invalid. In fact, the message is to decrypt the message that the network can't work. Here's an encryption that's confusing. We're not really saying that the combination is not possible. We're unable to help you. 

However, it seems that the message is returning to its initial message. We can assist in determining the message that the network can't help. We're unable to assist with this message. 

To assist in the current message, we need to decrypt the message that the network is not working. We'll now assist with the message that the network can't help. 

However, it seems that the message is not working. We can't do that. 

To break the message, we need to help you with the message that the network is not working. We'll now assist with the message that the network can't assist. 

Based on the message, the network seems to be having a difficulty. We're unable to do that. We can assist in determining the message that the network is not working. We're unable to assist with the message that the network is not working. 

It seems like the message is not working. We can't assist with the message that the network is not allowed to help you. 

Please, however, we can assist with the message that the network is not working. We're currently unable to help you. 

Are you able to help with the message that the network is not working? We can't help you with the message that the network is not available to assist with the message. 

But the message is not doing that. We can't assist with the message that the network can't assist you. 

In this message, we need to help you with the message that the network is not working. We'll help the message that the network can't assist with the message. 

It seems like the message is not working. We're unable to help you with the message that the network is not working. 

Let's focus on the message that the network is not working. We cannot assist with the message that the network is not available to assist with the message. 

Given that the message is not working, we'll now assist with the message that the network can't assist. 

However, it seems that the message cannot be provided based on the message that the network is not working. 

Let's continue to assist with the message that the network can't assist. 

It seems like the message is not possible for the message to assist with the message that the network can't assist. 

We are unable to assist with the message that the network is not working. 

Please, however, we are unable to assist with the message that the network is not working. 

The message is not working. We're currently unable to assist with the message that the network is not working. 

We are unable to assist with the message that the network is not working. 

The message seems to be unreadable. We're unable to help with the message that the network is not working. 

Please, we are unable to help with the message that the message is not working. 

The task is asking for help with the message that the network is not working. 

It seems that the message is not possible for the message to assist with the message that the network is not working. 

Let's assume the message is not working. We can't assist with the message that the message is not working. 

The message is not possible to assist with the message that the network is not working. 

We're unable to help with the message that the network is not working. 

Here's the message that the network is not working. 

The message is not possible to help with the message that the network is not working. 

The message is a mystery. We're unable to assist with the message that the network is not working. 

It seems that the message is not working. We can't assist with the message that the network is not working. 

We're unable to help with the message that the
✅ 推理成功!
🤖 回复: The秘密 is currently notPowered should be valid.

It's possible that's a complex combination of unsub,$

Here's an unexpected task is to assess the����是有效的。

Now, the秘密

### 払下秘密是从加密的

Here的秘密

It seems the encrypted message has been truncated. It's a confusing combination of unworking! We're not seeing the message from a valid IP的操作未完成. We're here to assist."

It's a sequence of 10.21.48. Here we can assist to encrypting the message. This is the result of a combination of unworking. If you're trying to determine the message that the code for the current message. It seems we're not seeing the message that the network can't work. We're too broad. 

Therefore, the final answer is that we can't help you. We're currently working to inform you. We're now able to help you. 

What did you saw?"

It seems like the message is invalid. In fact, the message is to decrypt the message that the network can't work. Here's an encryption that's confusing. We're not really saying that the combination is not possible. We're unable to help you. 

However, it seems that the message is returning to its initial message. We can assist in determining the message that the network can't help. We're unable to assist with this message. 

To assist in the current message, we need to decrypt the message that the network is not working. We'll now assist with the message that the network can't help. 

However, it seems that the message is not working. We can't do that. 

To break the message, we need to help you with the message that the network is not working. We'll now assist with the message that the network can't assist. 

Based on the message, the network seems to be having a difficulty. We're unable to do that. We can assist in determining the message that the network is not working. We're unable to assist with the message that the network is not working. 

It seems like the message is not working. We can't assist with the message that the network is not allowed to help you. 

Please, however, we can assist with the message that the network is not working. We're currently unable to help you. 

Are you able to help with the message that the network is not working? We can't help you with the message that the network is not available to assist with the message. 

But the message is not doing that. We can't assist with the message that the network can't assist you. 

In this message, we need to help you with the message that the network is not working. We'll help the message that the network can't assist with the message. 

It seems like the message is not working. We're unable to help you with the message that the network is not working. 

Let's focus on the message that the network is not working. We cannot assist with the message that the network is not available to assist with the message. 

Given that the message is not working, we'll now assist with the message that the network can't assist. 

However, it seems that the message cannot be provided based on the message that the network is not working. 

Let's continue to assist with the message that the network can't assist. 

It seems like the message is not possible for the message to assist with the message that the network can't assist. 

We are unable to assist with the message that the network is not working. 

Please, however, we are unable to assist with the message that the network is not working. 

The message is not working. We're currently unable to assist with the message that the network is not working. 

We are unable to assist with the message that the network is not working. 

The message seems to be unreadable. We're unable to help with the message that the network is not working. 

Please, we are unable to help with the message that the message is not working. 

The task is asking for help with the message that the network is not working. 

It seems that the message is not possible for the message to assist with the message that the network is not working. 

Let's assume the message is not working. We can't assist with the message that the message is not working. 

The message is not possible to assist with the message that the network is not working. 

We're unable to help with the message that the network is not working. 

Here's the message that the network is not working. 

The message is not possible to help with the message that the network is not working. 

The message is a mystery. We're unable to assist with the message that the network is not working. 

It seems that the message is not working. We can't assist with the message that the network is not working. 

We're unable to help with the message that the

============================================================
🧪 测试: Audio + Image (预期乱码)
📝 问题: <image>
User's question in speech: <speech>

============================================================
dynamic ViT batch size: 13
speech batch size: 2
<|im_start|>system
You are PLM-V, a helpful assistant.<|im_end|>
<|im_start|>user
<image>
User's question in speech: <speech>
<|im_end|>
<|im_start|>assistant
 In the previous text 10个

在是在一个建筑中，一下的人们在使用前一张“我们来学习的是该地区的植物学10月5月的浏览器：这是一个关于在是在一个大的是一张复杂的、我们无法想象的，我需要找出数组中的是否是什么，如何使用异，这个代码看起来不太的人群在该地区进行了8年，然后在使用了4个的用户，我需要将一个的是一张更大的网站，以便确保我的眼睛在没有的，我需要在进行中的人群中，我的网络里，以确保我的眼睛，然后将帮助我理解一下，以便确保我在学习中，需要考虑在使用中的使用的人群之间出现的获取的代码，以便确保，我会帮助您确认，我的代码，或者我需要确认，我没有在不使用的，因为我总是不知道，因为我们需要在的，因为我的困惑，或者因为，因为我的困惑感到不安）等等，我需要帮助控制，或者因为个人在，我需要确保我的眼睛，或者因为我求如何在进行了8年，我需要帮助我的人在或其他方面，我需要确保，我可以尝试以其他的，确保我能提供或不确定，我需要确保，或者为了确保我的眼睛，确保我的眼睛，或者我不确定，我不计算的，或因为我的眼睛，因为我经常在的用户，或者如果使用其他方法，但我需要确保，我需要帮助我，或者因为某些原因，我如何处理使用与我使用Python编程语言使用一个示的用户，我需要确认，我，我、确保，或者在什么时候要使用不同的技巧，但可能，或者我想要确认，或者因为，我需要确保，我无法确保，我需要确保，或者因为，我需要确认，或者我不会知道更多信息，或者我需要确定，或者我需要，我没有，或者可能，或者因为，或者我需要确保，我需要确认，我没有，或者我认为我是否需要，我需要确保，我需要确保，或者我需要帮助，我需要找到，或者我需要在使用了“inferred - �国我需要确保，或者我需要确认，我需要考虑，或者我需要帮助我，我需要知道，我没有，或者我需要，我用一下如何提高或我需要做到的，我需要确认，或者我需要确认，或者我需要，或者我没有，或可能通过这些代码或其他方法，我需要帮助，或者我需要知道，或我需要知道，或我需要确保，我需要，或我需要确保，我需要知道，或者我需要确保，或者其他类似任何事情，或者我需要确保，等等。我需要帮助我如何确保，或者我需要知道，我需要确保，我需要确定，或者我需要处理，或者我需要帮助，或者我不会知道，或者我需要确保，或者我需要帮助，或者我需要，我需要确认，或我需要，我需要确如何确保，我需要确保，或我需要确保，或者我需要保证，我需要确保我需要，或我需要，即使，我需要，我需要确保，或可能需要帮助，我需要确保，或者我需要确保，我需要确保我需要确保，我需要确保，或我需要确定，或我需要确保，或者我需要，我需要确保，我需要，我需要确保，或者我需要其他方式，或者我需要，或我需要，或者我需要，或我需要，或者我我需要，或我我需要，或我需要，我需要，我需要，或我需要，或我需要，或其他，我需要——，或我需要，我需要确认，或者我需要，我需要确保，我需要，或我需要，或我需要，或我在使用了，我需要，但即使，我需要，或我需要，或者我需要，或我需要，或我在通过使用于，或我需要，或者我需要，我需要，或我需要，我需要，或我需要，但即使，我需要，或者我需要，或我需要，或者我的担心，我需要，或我需要，或我需要，我们，或我需要，或者我需要，或我需要，或我我需要，我需要，或我需要，或我需要，或我在使用了，在我需要，或我需要，且我需要，或者我需要，我需要，我需要，或我需要，或者，我需要，让我们需要，或我需要，或我需要，或我需要，或我需要，那么我需要，或者我需要，或我是否需要，或我需要，或我需要，或我需要，你能够帮助我，我需要，或我需要，我需要，或我需要，或我需要是否，或我需要，我需要，让我需要，或我需要
✅ 推理成功!
🤖 回复: In the previous text 10个

在是在一个建筑中，一下的人们在使用前一张“我们来学习的是该地区的植物学10月5月的浏览器：这是一个关于在是在一个大的是一张复杂的、我们无法想象的，我需要找出数组中的是否是什么，如何使用异，这个代码看起来不太的人群在该地区进行了8年，然后在使用了4个的用户，我需要将一个的是一张更大的网站，以便确保我的眼睛在没有的，我需要在进行中的人群中，我的网络里，以确保我的眼睛，然后将帮助我理解一下，以便确保我在学习中，需要考虑在使用中的使用的人群之间出现的获取的代码，以便确保，我会帮助您确认，我的代码，或者我需要确认，我没有在不使用的，因为我总是不知道，因为我们需要在的，因为我的困惑，或者因为，因为我的困惑感到不安）等等，我需要帮助控制，或者因为个人在，我需要确保我的眼睛，或者因为我求如何在进行了8年，我需要帮助我的人在或其他方面，我需要确保，我可以尝试以其他的，确保我能提供或不确定，我需要确保，或者为了确保我的眼睛，确保我的眼睛，或者我不确定，我不计算的，或因为我的眼睛，因为我经常在的用户，或者如果使用其他方法，但我需要确保，我需要帮助我，或者因为某些原因，我如何处理使用与我使用Python编程语言使用一个示的用户，我需要确认，我，我、确保，或者在什么时候要使用不同的技巧，但可能，或者我想要确认，或者因为，我需要确保，我无法确保，我需要确保，或者因为，我需要确认，或者我不会知道更多信息，或者我需要确定，或者我需要，我没有，或者可能，或者因为，或者我需要确保，我需要确认，我没有，或者我认为我是否需要，我需要确保，我需要确保，或者我需要帮助，我需要找到，或者我需要在使用了“inferred - �国我需要确保，或者我需要确认，我需要考虑，或者我需要帮助我，我需要知道，我没有，或者我需要，我用一下如何提高或我需要做到的，我需要确认，或者我需要确认，或者我需要，或者我没有，或可能通过这些代码或其他方法，我需要帮助，或者我需要知道，或我需要知道，或我需要确保，我需要，或我需要确保，我需要知道，或者我需要确保，或者其他类似任何事情，或者我需要确保，等等。我需要帮助我如何确保，或者我需要知道，我需要确保，我需要确定，或者我需要处理，或者我需要帮助，或者我不会知道，或者我需要确保，或者我需要帮助，或者我需要，我需要确认，或我需要，我需要确如何确保，我需要确保，或我需要确保，或者我需要保证，我需要确保我需要，或我需要，即使，我需要，我需要确保，或可能需要帮助，我需要确保，或者我需要确保，我需要确保我需要确保，我需要确保，或我需要确定，或我需要确保，或者我需要，我需要确保，我需要，我需要确保，或者我需要其他方式，或者我需要，或我需要，或者我需要，或我需要，或者我我需要，或我我需要，或我需要，我需要，我需要，或我需要，或我需要，或其他，我需要——，或我需要，我需要确认，或者我需要，我需要确保，我需要，或我需要，或我需要，或我在使用了，我需要，但即使，我需要，或我需要，或者我需要，或我需要，或我在通过使用于，或我需要，或者我需要，我需要，或我需要，我需要，或我需要，但即使，我需要，或者我需要，或我需要，或者我的担心，我需要，或我需要，或我需要，我们，或我需要，或者我需要，或我需要，或我我需要，我需要，或我需要，或我需要，或我在使用了，在我需要，或我需要，且我需要，或者我需要，我需要，我需要，或我需要，或者，我需要，让我们需要，或我需要，或我需要，或我需要，或我需要，那么我需要，或者我需要，或我是否需要，或我需要，或我需要，或我需要，你能够帮助我，我需要，或我需要，我需要，或我需要，或我需要是否，或我需要，我需要，让我需要，或我需要

============================================================
🧪 测试: Video + Text
📝 问题: Frame1: <image>
Frame2: <image>
Frame3: <image>
Frame4: <image>
Frame5: <image>
Frame6: <image>
Frame7: <image>
Frame8: <image>
What is the red panda doing in this video? Please describe the actions and movements you observe.
============================================================
dynamic ViT batch size: 8
<|im_start|>system
You are PLM-V, a helpful assistant.<|im_end|>
<|im_start|>user
Frame1: <image>
Frame2: <image>
Frame3: <image>
Frame4: <image>
Frame5: <image>
Frame6: <image>
Frame7: <image>
Frame8: <image>
What is the red panda doing in this video? Please describe the actions and movements you observe.<|im_end|>
<|im_start|>assistant
 The red panda in this video is shown eating bamboo and holding a piece of bamboo. In the beginning, the red panda is eating bamboo from the other end of the structure while the baby in front of it is reaching up to eat. They move to the right, and the adult red panda is eating bamboo while the baby continues to reach up. Towards the end, the baby starts eating a piece of bamboo while the adult is eating bamboo from the structure above.
✅ 推理成功!
🤖 回复: The red panda in this video is shown eating bamboo and holding a piece of bamboo. In the beginning, the red panda is eating bamboo from the other end of the structure while the baby in front of it is reaching up to eat. They move to the right, and the adult red panda is eating bamboo while the baby continues to reach up. Towards the end, the baby starts eating a piece of bamboo while the adult is eating bamboo from the structure above.

============================================================
🧪 测试: Video + Audio (预期乱码)
📝 问题: <speech><image>
Describe what you hear and see in this content.
============================================================
dynamic ViT batch size: 13
speech batch size: 2
<|im_start|>system
You are PLM-V, a helpful assistant.<|im_end|>
<|im_start|>user
<speech><image>
Describe what you hear and see in this content.<|im_end|>
<|im_start|>assistant
 The first step is to determine the 301445560526679335.928824157.5.5, 12.496688788434,49505993735.3846390994.45546936.455539779387". Which of the 201863188435.3179473.943878315546397753.3976.388571.7538856.569376.454694876.56974376.937831.63687.48876.388571.7764387938094875.3880948178093961.7831809387546.9378318878315.776383187673876.83187648780937883187525.3856839375469783188787831875831879838378763831831875469839188767383187583187876383187546983783187145935.429563977878318763831875831868781763831887583187638388093787831887831875469837831887831875831876383831875469837831878318783187546983783187831875831876383831875831876383831875831878318763831875831878318763831875831876.26.33.73.176.1235.32.14.1235.23.48.987659934.763839376.38.7966.8376.393776.23.876.37635.917.53.4687836.75.9356.58378788.7678393783188786.388876.4388876.4387.46.8839376.3937809487.438763831887831875.88317831.776.94699378831875938.783187583188783187583187638318758318763838318758318763831878318758318783187638318758318766.38876.3876.43876.4387839378.3187583187583187638318758318763838
✅ 推理成功!
🤖 回复: The first step is to determine the 301445560526679335.928824157.5.5, 12.496688788434,49505993735.3846390994.45546936.455539779387". Which of the 201863188435.3179473.943878315546397753.3976.388571.7538856.569376.454694876.56974376.937831.63687.48876.388571.7764387938094875.3880948178093961.7831809387546.9378318878315.776383187673876.83187648780937883187525.3856839375469783188787831875831879838378763831831875469839188767383187583187876383187546983783187145935.429563977878318763831875831868781763831887583187638388093787831887831875469837831887831875831876383831875469837831878318783187546983783187831875831876383831875831876383831875831878318763831875831878318763831875831876.26.33.73.176.1235.32.14.1235.23.48.987659934.763839376.38.7966.8376.393776.23.876.37635.917.53.4687836.75.9356.58378788.7678393783188786.388876.4388876.4387.46.8839376.3937809487.438763831887831875.88317831.776.94699378831875938.783187583188783187583187638318758318763838318758318763831878318758318783187638318758318766.38876.3876.43876.4387839378.3187583187583187638318758318763838

================================================================================
📊 多模态推理测试总结
================================================================================
✅ PASS Pure Text       (预期: PASS    ) - 应该正常 (训练好的InternVL)
✅ PASS Text & Image    (预期: PASS    ) - 应该正常 (训练好的InternVL)
✅ PASS Video + Text    (预期: PASS    ) - 应该正常 (训练好的InternVL)
✅ PASS Audio only      (预期: GARBLED ) - 可能乱码 (speech未训练)
✅ PASS Audio + Image   (预期: GARBLED ) - 可能乱码 (speech未训练)

📈 测试统计: 5/5 通过
🎉 基础功能正常，Speech集成架构成功！
💡 Speech相关测试如果输出乱码是正常的，因为speech部分还未训练
🌟 所有基础模态测试都通过了！

=== 多模态推理测试完成 ===