voicescribe-gigaam / v3_e2e_rnnt_joint.xml
Andrewsab's picture
Voice Scribe mirror gigaam from Andrewsab/gigaam-v3-e2e-rnnt-ov@dff16933a640
4ebe334 verified
Raw
History Blame Contribute Delete
13.7 kB
<?xml version="1.0"?>
<net name="main_graph" version="11">
<layers>
<layer id="1" name="enc" type="Parameter" version="opset1">
<data shape="1,768,1" element_type="f32" />
<output>
<port id="0" precision="FP32" names="enc">
<dim>1</dim>
<dim>768</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="0" name="dec" type="Parameter" version="opset1">
<data shape="1,320,1" element_type="f32" />
<output>
<port id="0" precision="FP32" names="dec">
<dim>1</dim>
<dim>320</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="2" name="Constant_40626_compressed" type="Const" version="opset1">
<data element_type="f16" shape="1, 1, 1, 1025" offset="0" size="2050" />
<output>
<port id="0" precision="FP16">
<dim>1</dim>
<dim>1</dim>
<dim>1</dim>
<dim>1025</dim>
</port>
</output>
</layer>
<layer id="3" name="Constant_40626" type="Convert" version="opset1">
<data destination_type="f32" />
<rt_info>
<attribute name="decompression" version="0" />
</rt_info>
<input>
<port id="0" precision="FP16">
<dim>1</dim>
<dim>1</dim>
<dim>1</dim>
<dim>1025</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1</dim>
<dim>1025</dim>
</port>
</output>
</layer>
<layer id="4" name="Constant_40624_compressed" type="Const" version="opset1">
<data element_type="f16" shape="1, 1, 320" offset="2050" size="640" />
<output>
<port id="0" precision="FP16">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="5" name="Constant_40624" type="Convert" version="opset1">
<data destination_type="f32" />
<rt_info>
<attribute name="decompression" version="0" />
</rt_info>
<input>
<port id="0" precision="FP16">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="6" name="Transpose_40471_compressed" type="Const" version="opset1">
<data element_type="f16" shape="320, 768" offset="2690" size="491520" />
<output>
<port id="0" precision="FP16">
<dim>320</dim>
<dim>768</dim>
</port>
</output>
</layer>
<layer id="7" name="Transpose_40471" type="Convert" version="opset1">
<data destination_type="f32" />
<rt_info>
<attribute name="decompression" version="0" />
</rt_info>
<input>
<port id="0" precision="FP16">
<dim>320</dim>
<dim>768</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>320</dim>
<dim>768</dim>
</port>
</output>
</layer>
<layer id="8" name="/enc/MatMul" type="MatMul" version="opset1">
<data transpose_a="true" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>768</dim>
<dim>1</dim>
</port>
<port id="1" precision="FP32">
<dim>320</dim>
<dim>768</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="/enc/MatMul_output_0">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="9" name="/enc/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="/enc/Add_output_0">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="10" name="/Constant" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="494210" size="8" />
<output>
<port id="0" precision="I64" names="/Constant_output_0">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="11" name="/Unsqueeze" type="Unsqueeze" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="/Unsqueeze_output_0">
<dim>1</dim>
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="12" name="Constant_40625_compressed" type="Const" version="opset1">
<data element_type="f16" shape="1, 1, 320" offset="494218" size="640" />
<output>
<port id="0" precision="FP16">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="13" name="Constant_40625" type="Convert" version="opset1">
<data destination_type="f32" />
<rt_info>
<attribute name="decompression" version="0" />
</rt_info>
<input>
<port id="0" precision="FP16">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="14" name="Transpose_40478_compressed" type="Const" version="opset1">
<data element_type="f16" shape="320, 320" offset="494858" size="204800" />
<output>
<port id="0" precision="FP16">
<dim>320</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="15" name="Transpose_40478" type="Convert" version="opset1">
<data destination_type="f32" />
<rt_info>
<attribute name="decompression" version="0" />
</rt_info>
<input>
<port id="0" precision="FP16">
<dim>320</dim>
<dim>320</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>320</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="16" name="/pred/MatMul" type="MatMul" version="opset1">
<data transpose_a="true" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>320</dim>
<dim>1</dim>
</port>
<port id="1" precision="FP32">
<dim>320</dim>
<dim>320</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="/pred/MatMul_output_0">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="17" name="/pred/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="/pred/Add_output_0">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="18" name="/Constant_1" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="699658" size="8" />
<output>
<port id="0" precision="I64" names="/Constant_1_output_0">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="19" name="/Unsqueeze_1" type="Unsqueeze" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="/Unsqueeze_1_output_0">
<dim>1</dim>
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="20" name="/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="/Add_output_0">
<dim>1</dim>
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="21" name="/joint_net/joint_net.0/Relu" type="ReLU" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="/joint_net/joint_net.0/Relu_output_0">
<dim>1</dim>
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="22" name="Transpose_40487_compressed" type="Const" version="opset1">
<data element_type="f16" shape="1025, 320" offset="699666" size="656000" />
<output>
<port id="0" precision="FP16">
<dim>1025</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="23" name="Transpose_40487" type="Convert" version="opset1">
<data destination_type="f32" />
<rt_info>
<attribute name="decompression" version="0" />
</rt_info>
<input>
<port id="0" precision="FP16">
<dim>1025</dim>
<dim>320</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1025</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="24" name="/joint_net/joint_net.1/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>1</dim>
<dim>320</dim>
</port>
<port id="1" precision="FP32">
<dim>1025</dim>
<dim>320</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="/joint_net/joint_net.1/MatMul_output_0">
<dim>1</dim>
<dim>1</dim>
<dim>1</dim>
<dim>1025</dim>
</port>
</output>
</layer>
<layer id="25" name="/joint_net/joint_net.1/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1</dim>
<dim>1025</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1</dim>
<dim>1025</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="/joint_net/joint_net.1/Add_output_0">
<dim>1</dim>
<dim>1</dim>
<dim>1</dim>
<dim>1025</dim>
</port>
</output>
</layer>
<layer id="26" name="joint" type="LogSoftmax" version="opset5">
<data axis="-1" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1</dim>
<dim>1025</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="joint">
<dim>1</dim>
<dim>1</dim>
<dim>1</dim>
<dim>1025</dim>
</port>
</output>
</layer>
<layer id="27" name="joint/sink_port_0" type="Result" version="opset1" output_names="joint">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1</dim>
<dim>1025</dim>
</port>
</input>
</layer>
</layers>
<edges>
<edge from-layer="0" from-port="0" to-layer="16" 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="3" to-port="0" />
<edge from-layer="3" from-port="1" to-layer="25" to-port="0" />
<edge from-layer="4" from-port="0" to-layer="5" to-port="0" />
<edge from-layer="5" from-port="1" to-layer="9" to-port="0" />
<edge from-layer="6" from-port="0" to-layer="7" to-port="0" />
<edge from-layer="7" from-port="1" to-layer="8" to-port="1" />
<edge from-layer="8" from-port="2" to-layer="9" to-port="1" />
<edge from-layer="9" from-port="2" to-layer="11" to-port="0" />
<edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
<edge from-layer="11" from-port="2" to-layer="20" to-port="0" />
<edge from-layer="12" from-port="0" to-layer="13" to-port="0" />
<edge from-layer="13" from-port="1" to-layer="17" to-port="0" />
<edge from-layer="14" from-port="0" to-layer="15" to-port="0" />
<edge from-layer="15" from-port="1" to-layer="16" to-port="1" />
<edge from-layer="16" from-port="2" to-layer="17" to-port="1" />
<edge from-layer="17" from-port="2" to-layer="19" to-port="0" />
<edge from-layer="18" from-port="0" to-layer="19" to-port="1" />
<edge from-layer="19" from-port="2" to-layer="20" to-port="1" />
<edge from-layer="20" from-port="2" to-layer="21" to-port="0" />
<edge from-layer="21" from-port="1" to-layer="24" to-port="0" />
<edge from-layer="22" from-port="0" to-layer="23" to-port="0" />
<edge from-layer="23" from-port="1" to-layer="24" to-port="1" />
<edge from-layer="24" from-port="2" to-layer="25" to-port="1" />
<edge from-layer="25" from-port="2" to-layer="26" to-port="0" />
<edge from-layer="26" from-port="1" to-layer="27" to-port="0" />
</edges>
<rt_info>
<Runtime_version value="2025.4.1-20426-82bbf0292c5-releases/2025/4" />
<conversion_parameters>
<input_model value="DIR\v3_e2e_rnnt_joint.onnx" />
<is_python_object value="False" />
</conversion_parameters>
</rt_info>
</net>