<?xml version="1.0"?>
<net name="Model24" version="11">
<layers>
<layer id="0" name="video_tokens" type="Parameter" version="opset1">
<data shape="?,?,32" element_type="f32" />
<output>
<port id="0" precision="FP32" names="video_tokens">
<dim>-1</dim>
<dim>-1</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="1" name="audio_tokens" type="Parameter" version="opset1">
<data shape="?,?,32" element_type="f32" />
<output>
<port id="0" precision="FP32" names="audio_tokens">
<dim>-1</dim>
<dim>-1</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="2" name="__module.attention_pooler/aten::unsqueeze/Unsqueeze" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 16" offset="0" size="64" />
<output>
<port id="0" precision="FP32" names="60">
<dim>1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="3" name="self.video_input_proj.weight" type="Const" version="opset1">
<data element_type="f32" shape="16, 32" offset="64" size="2048" />
<output>
<port id="0" precision="FP32" names="self.video_input_proj.weight">
<dim>16</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="4" name="__module.video_input_proj/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>16</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="5" name="Constant_163519" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 16" offset="2112" size="64" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="6" name="aten::add/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="17">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="7" name="self.audio_input_proj.weight" type="Const" version="opset1">
<data element_type="f32" shape="16, 32" offset="2176" size="2048" />
<output>
<port id="0" precision="FP32" names="self.audio_input_proj.weight">
<dim>16</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="8" name="__module.audio_input_proj/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>16</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="9" name="Constant_163520" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 16" offset="4224" size="64" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="10" name="aten::add/Add_1" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="25">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="11" name="aten::cat/Concat" type="Concat" version="opset1">
<data axis="1" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="28,tokens">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="12" name="self.attention_pooler.to_k.weight" type="Const" version="opset1">
<data element_type="f32" shape="16, 16" offset="4288" size="1024" />
<output>
<port id="0" precision="FP32" names="self.attention_pooler.to_k.weight">
<dim>16</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="13" name="__module.attention_pooler.to_k/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
<port id="1" precision="FP32">
<dim>16</dim>
<dim>16</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="14" name="Constant_163522" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 16" offset="5312" size="64" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="15" name="__module.attention_pooler.to_k/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="71">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="16" name="ShapeOf_163581" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="17" name="Constant_163582" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="5376" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="18" name="Constant_163583" type="Const" version="opset1">
<data element_type="i64" shape="" offset="5376" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="19" name="Gather_163584" type="Gather" version="opset8">
<data batch_dims="0" />
<input>
<port id="0" precision="I64">
<dim>3</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64" />
</input>
<output>
<port id="3" precision="I64" names="61">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="20" name="Constant_162948" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="5384" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="21" name="Constant_162950" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="5384" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="22" name="__module.attention_pooler/prim::ListConstruct/SequenceMark" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="23" name="__module.attention_pooler/aten::expand/Broadcast" type="Broadcast" version="opset3">
<data mode="bidirectional" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
<port id="1" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="63,input.5">
<dim>-1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="24" name="self.attention_pooler.to_q.weight" type="Const" version="opset1">
<data element_type="f32" shape="16, 16" offset="5392" size="1024" />
<output>
<port id="0" precision="FP32" names="self.attention_pooler.to_q.weight">
<dim>16</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="25" name="__module.attention_pooler.to_q/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
<port id="1" precision="FP32">
<dim>16</dim>
<dim>16</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="26" name="Constant_163521" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 16" offset="6416" size="64" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="27" name="__module.attention_pooler.to_q/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="66">
<dim>-1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="28" name="Constant_163564" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="6480" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="29" name="__module.attention_pooler/aten::permute/Transpose" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="80,query">
<dim>-1</dim>
<dim>2</dim>
<dim>1</dim>
<dim>8</dim>
</port>
</output>
</layer>
<layer id="30" name="Constant_163593" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="6512" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="31" name="__module.attention_pooler/aten::unflatten/Reshape_1" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="73,x.3">
<dim>-1</dim>
<dim>-1</dim>
<dim>2</dim>
<dim>8</dim>
</port>
</output>
</layer>
<layer id="32" name="Constant_160744" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="6544" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="33" name="__module.attention_pooler/aten::permute/Transpose_1" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>2</dim>
<dim>8</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="82,key">
<dim>-1</dim>
<dim>2</dim>
<dim>-1</dim>
<dim>8</dim>
</port>
</output>
</layer>
<layer id="34" name="self.attention_pooler.to_v.weight" type="Const" version="opset1">
<data element_type="f32" shape="16, 16" offset="6576" size="1024" />
<output>
<port id="0" precision="FP32" names="self.attention_pooler.to_v.weight">
<dim>16</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="35" name="__module.attention_pooler.to_v/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
<port id="1" precision="FP32">
<dim>16</dim>
<dim>16</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="36" name="Constant_163523" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 16" offset="7600" size="64" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="37" name="__module.attention_pooler.to_v/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="76">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="38" name="Constant_163594" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="6512" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="39" name="__module.attention_pooler/aten::unflatten/Reshape_2" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="78,x">
<dim>-1</dim>
<dim>-1</dim>
<dim>2</dim>
<dim>8</dim>
</port>
</output>
</layer>
<layer id="40" name="Constant_160760" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="6544" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="41" name="__module.attention_pooler/aten::permute/Transpose_2" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>2</dim>
<dim>8</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="84,value">
<dim>-1</dim>
<dim>2</dim>
<dim>-1</dim>
<dim>8</dim>
</port>
</output>
</layer>
<layer id="42" name="__module.attention_pooler/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
<data causal="false" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>2</dim>
<dim>1</dim>
<dim>8</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>2</dim>
<dim>-1</dim>
<dim>8</dim>
</port>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>2</dim>
<dim>-1</dim>
<dim>8</dim>
</port>
</input>
<output>
<port id="3" precision="FP32" names="85,out">
<dim>-1</dim>
<dim>2</dim>
<dim>1</dim>
<dim>8</dim>
</port>
</output>
</layer>
<layer id="43" name="Constant_163699" type="Const" version="opset1">
<data element_type="i64" shape="3" offset="7664" size="24" />
<output>
<port id="0" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="44" name="__module.attention_pooler/aten::flatten/Reshape" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>2</dim>
<dim>1</dim>
<dim>8</dim>
</port>
<port id="1" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="88,input.7">
<dim>-1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="45" name="self.attention_pooler.to_out.weight" type="Const" version="opset1">
<data element_type="f32" shape="16, 16" offset="7688" size="1024" />
<output>
<port id="0" precision="FP32" names="self.attention_pooler.to_out.weight">
<dim>16</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="46" name="__module.attention_pooler.to_out/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
<port id="1" precision="FP32">
<dim>16</dim>
<dim>16</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="47" name="Constant_163524" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 16" offset="8712" size="64" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="48" name="__module.attention_pooler.to_out/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="91">
<dim>-1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="49" name="Concat_161244" type="Const" version="opset1">
<data element_type="i64" shape="2" offset="8776" size="16" />
<output>
<port id="0" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="50" name="aten::flatten/Reshape" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
<port id="1" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="32,input.9">
<dim>-1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="51" name="self.mlp_hidden.weight" type="Const" version="opset1">
<data element_type="f32" shape="16, 16" offset="8792" size="1024" />
<output>
<port id="0" precision="FP32" names="self.mlp_hidden.weight">
<dim>16</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="52" name="__module.mlp_hidden/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>16</dim>
</port>
<port id="1" precision="FP32">
<dim>16</dim>
<dim>16</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="53" name="Constant_163525" type="Const" version="opset1">
<data element_type="f32" shape="1, 16" offset="9816" size="64" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="54" name="__module.mlp_hidden/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>16</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>16</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="94">
<dim>-1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="55" name="aten::gelu/Gelu" type="Gelu" version="opset7">
<data approximation_mode="TANH" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>16</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="35,input">
<dim>-1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="56" name="self.mlp_out.weight" type="Const" version="opset1">
<data element_type="f32" shape="1, 16" offset="9880" size="64" />
<output>
<port id="0" precision="FP32" names="self.mlp_out.weight">
<dim>1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="57" name="__module.mlp_out/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>16</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>16</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="58" name="Constant_163526" type="Const" version="opset1">
<data element_type="f32" shape="1, 1" offset="9944" size="4" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="59" name="__module.mlp_out/aten::linear/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>1</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="97">
<dim>-1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="60" name="37" type="Const" version="opset1">
<data element_type="i64" shape="" offset="9952" size="8" />
<output>
<port id="0" precision="I64" names="37" />
</output>
</layer>
<layer id="61" name="aten::squeeze/Squeeze" type="Squeeze" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>1</dim>
</port>
<port id="1" precision="I64" />
</input>
<output>
<port id="2" precision="FP32" names="38,log_duration">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="62" name="aten::exp/Exp" type="Exp" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="duration">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="63" name="Result_160868" type="Result" version="opset1" output_names="duration">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
</port>
</input>
</layer>
</layers>
<edges>
<edge from-layer="0" from-port="0" to-layer="4" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="8" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="23" to-port="0" />
<edge from-layer="3" from-port="0" to-layer="4" to-port="1" />
<edge from-layer="4" from-port="2" to-layer="6" to-port="0" />
<edge from-layer="5" from-port="0" to-layer="6" to-port="1" />
<edge from-layer="6" from-port="2" to-layer="11" to-port="0" />
<edge from-layer="7" from-port="0" to-layer="8" to-port="1" />
<edge from-layer="8" from-port="2" to-layer="10" to-port="0" />
<edge from-layer="9" from-port="0" to-layer="10" to-port="1" />
<edge from-layer="10" from-port="2" to-layer="11" to-port="1" />
<edge from-layer="11" from-port="2" to-layer="13" to-port="0" />
<edge from-layer="11" from-port="2" to-layer="35" to-port="0" />
<edge from-layer="12" from-port="0" to-layer="13" to-port="1" />
<edge from-layer="13" from-port="2" to-layer="15" to-port="0" />
<edge from-layer="14" from-port="0" to-layer="15" to-port="1" />
<edge from-layer="15" from-port="2" to-layer="16" to-port="0" />
<edge from-layer="15" from-port="2" to-layer="31" to-port="0" />
<edge from-layer="16" from-port="1" to-layer="19" to-port="0" />
<edge from-layer="17" from-port="0" to-layer="19" to-port="1" />
<edge from-layer="18" from-port="0" to-layer="19" to-port="2" />
<edge from-layer="19" from-port="3" to-layer="22" to-port="0" />
<edge from-layer="20" from-port="0" to-layer="22" to-port="1" />
<edge from-layer="21" from-port="0" to-layer="22" to-port="2" />
<edge from-layer="22" from-port="3" to-layer="23" to-port="1" />
<edge from-layer="23" from-port="2" to-layer="25" to-port="0" />
<edge from-layer="24" from-port="0" to-layer="25" to-port="1" />
<edge from-layer="25" from-port="2" to-layer="27" to-port="0" />
<edge from-layer="26" from-port="0" to-layer="27" to-port="1" />
<edge from-layer="27" from-port="2" to-layer="29" to-port="0" />
<edge from-layer="28" from-port="0" to-layer="29" to-port="1" />
<edge from-layer="29" from-port="2" to-layer="42" to-port="0" />
<edge from-layer="30" from-port="0" to-layer="31" to-port="1" />
<edge from-layer="31" from-port="2" to-layer="33" to-port="0" />
<edge from-layer="32" from-port="0" to-layer="33" to-port="1" />
<edge from-layer="33" from-port="2" to-layer="42" to-port="1" />
<edge from-layer="34" from-port="0" to-layer="35" to-port="1" />
<edge from-layer="35" from-port="2" to-layer="37" to-port="0" />
<edge from-layer="36" from-port="0" to-layer="37" to-port="1" />
<edge from-layer="37" from-port="2" to-layer="39" to-port="0" />
<edge from-layer="38" from-port="0" to-layer="39" to-port="1" />
<edge from-layer="39" from-port="2" to-layer="41" to-port="0" />
<edge from-layer="40" from-port="0" to-layer="41" to-port="1" />
<edge from-layer="41" from-port="2" to-layer="42" to-port="2" />
<edge from-layer="42" from-port="3" to-layer="44" to-port="0" />
<edge from-layer="43" from-port="0" to-layer="44" to-port="1" />
<edge from-layer="44" from-port="2" to-layer="46" to-port="0" />
<edge from-layer="45" from-port="0" to-layer="46" to-port="1" />
<edge from-layer="46" from-port="2" to-layer="48" to-port="0" />
<edge from-layer="47" from-port="0" to-layer="48" to-port="1" />
<edge from-layer="48" from-port="2" to-layer="50" to-port="0" />
<edge from-layer="49" from-port="0" to-layer="50" to-port="1" />
<edge from-layer="50" from-port="2" to-layer="52" to-port="0" />
<edge from-layer="51" from-port="0" to-layer="52" to-port="1" />
<edge from-layer="52" from-port="2" to-layer="54" to-port="0" />
<edge from-layer="53" from-port="0" to-layer="54" to-port="1" />
<edge from-layer="54" from-port="2" to-layer="55" to-port="0" />
<edge from-layer="55" from-port="1" to-layer="57" to-port="0" />
<edge from-layer="56" from-port="0" to-layer="57" to-port="1" />
<edge from-layer="57" from-port="2" to-layer="59" to-port="0" />
<edge from-layer="58" from-port="0" to-layer="59" to-port="1" />
<edge from-layer="59" from-port="2" to-layer="61" to-port="0" />
<edge from-layer="60" from-port="0" to-layer="61" to-port="1" />
<edge from-layer="61" from-port="2" to-layer="62" to-port="0" />
<edge from-layer="62" from-port="1" to-layer="63" to-port="0" />
</edges>
<rt_info>
<info name="OpenVINO Runtime" value="2026.5.0-23697-32776832f8d" />
<Runtime_version value="2026.5.0-23697-32776832f8d" />
<conversion_parameters>
<framework value="pytorch" />
<is_python_object value="True" />
</conversion_parameters>
<optimum>
<diffusers_version value="0.41.0" />
<optimum_intel_version value="2.3.0.dev0+8c40189b" />
<optimum_version value="2.3.0" />
<pytorch_version value="2.15.0" />
<transformers_version value="5.15.1" />
</optimum>
</rt_info>
</net>
<net name="Model24" version="11">
<layers>
<layer id="0" name="video_tokens" type="Parameter" version="opset1">
<data shape="?,?,32" element_type="f32" />
<output>
<port id="0" precision="FP32" names="video_tokens">
<dim>-1</dim>
<dim>-1</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="1" name="audio_tokens" type="Parameter" version="opset1">
<data shape="?,?,32" element_type="f32" />
<output>
<port id="0" precision="FP32" names="audio_tokens">
<dim>-1</dim>
<dim>-1</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="2" name="__module.attention_pooler/aten::unsqueeze/Unsqueeze" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 16" offset="0" size="64" />
<output>
<port id="0" precision="FP32" names="60">
<dim>1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="3" name="self.video_input_proj.weight" type="Const" version="opset1">
<data element_type="f32" shape="16, 32" offset="64" size="2048" />
<output>
<port id="0" precision="FP32" names="self.video_input_proj.weight">
<dim>16</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="4" name="__module.video_input_proj/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>16</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="5" name="Constant_163519" type="Const" version="opset1">
<data element_type="f32" shape="1, 1, 16" offset="2112" size="64" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="6" name="aten::add/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>16</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="17">
<dim>-1</dim>
<dim>-1</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="7" name="self.audio_input_proj.weight" type="Const" version="opset1">
<data element_type="f32" shape="16, 32" offset="2176" size="2048" />
<output>
<port id="0" precision="FP32" names="self.audio_input_proj.weight">
<dim>16</dim>