voicescribe-gigaam / v3_e2e_rnnt_decoder.xml
Andrewsab's picture
Voice Scribe mirror gigaam from Andrewsab/gigaam-v3-e2e-rnnt-ov@dff16933a640
4ebe334 verified
<?xml version="1.0"?>
<net name="main_graph" version="11">
<layers>
<layer id="2" name="x" type="Parameter" version="opset1">
<data shape="1,1" element_type="i64" />
<rt_info>
<attribute name="old_api_map_element_type" version="0" value="i32" />
</rt_info>
<output>
<port id="0" precision="I64" names="x">
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="1" name="h.1" type="Parameter" version="opset1">
<data shape="1,1,320" element_type="f32" />
<output>
<port id="0" precision="FP32" names="h.1">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="0" name="c.1" type="Parameter" version="opset1">
<data shape="1,1,320" element_type="f32" />
<output>
<port id="0" precision="FP32" names="c.1">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="3" name="embed.weight_compressed" type="Const" version="opset1">
<data element_type="f16" shape="1025, 320" offset="0" size="656000" />
<output>
<port id="0" precision="FP16" names="embed.weight">
<dim>1025</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="4" name="embed.weight" 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="5" name="Constant_8" type="Const" version="opset1">
<data element_type="i64" shape="" offset="656000" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="6" name="/embed/Gather" type="Gather" version="opset8">
<data batch_dims="0" />
<input>
<port id="0" precision="FP32">
<dim>1025</dim>
<dim>320</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
<dim>1</dim>
</port>
<port id="2" precision="I64" />
</input>
<output>
<port id="3" precision="FP32" names="/embed/Gather_output_0">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="7" name="Constant_41" type="Const" version="opset1">
<data element_type="i64" shape="3" offset="656008" size="24" />
<output>
<port id="0" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="8" name="Transpose_42" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
<port id="1" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="9" name="Constant_43" type="Const" version="opset1">
<data element_type="i64" shape="3" offset="656008" size="24" />
<output>
<port id="0" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="10" name="Transpose_44" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
<port id="1" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="11" name="ShapeOf_2208" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="12" name="ShapeOf_2207" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1025</dim>
<dim>320</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="13" name="Constant_2209" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="656032" size="8" />
<rt_info>
<attribute name="precise" version="0" />
</rt_info>
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="14" name="Constant_2206" type="Const" version="opset1">
<data element_type="i64" shape="" offset="656000" size="8" />
<rt_info>
<attribute name="precise" version="0" />
</rt_info>
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="15" name="Gather_2210" type="Gather" version="opset1">
<input>
<port id="0" precision="I64">
<dim>2</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64" />
</input>
<output>
<port id="3" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="16" name="ShapeOf_21" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>2</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="17" name="Constant_25" type="Const" version="opset1">
<data element_type="i32" shape="1" offset="656040" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="18" name="Constant_22" type="Const" version="opset1">
<data element_type="i32" shape="1" offset="656044" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="19" name="Gather_26" type="Gather" version="opset8">
<data batch_dims="0" />
<input>
<port id="0" precision="I64">
<dim>3</dim>
</port>
<port id="1" precision="I32">
<dim>1</dim>
</port>
<port id="2" precision="I32">
<dim>1</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="20" name="Constant_2100" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="656000" size="8" />
<rt_info>
<attribute name="precise" version="0" />
</rt_info>
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="21" name="Constant_2101" type="Const" version="opset1">
<data element_type="i64" shape="" offset="656000" size="8" />
<rt_info>
<attribute name="precise" version="0" />
</rt_info>
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="22" name="Gather_2102" 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">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="23" name="Broadcast_38" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="24" name="Concat_17_compressed" type="Const" version="opset1">
<data element_type="f16" shape="1, 1280, 320" offset="656048" size="819200" />
<output>
<port id="0" precision="FP16">
<dim>1</dim>
<dim>1280</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="25" name="Concat_17" 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>1280</dim>
<dim>320</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1280</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="26" name="Concat_20_compressed" type="Const" version="opset1">
<data element_type="f16" shape="1, 1280, 320" offset="1475248" size="819200" />
<output>
<port id="0" precision="FP16">
<dim>1</dim>
<dim>1280</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="27" name="Concat_20" 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>1280</dim>
<dim>320</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1280</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="28" name="Concat_37_compressed" type="Const" version="opset1">
<data element_type="f16" shape="1, 1280" offset="2294448" size="2560" />
<output>
<port id="0" precision="FP16">
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="29" name="Concat_37" 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>1280</dim>
</port>
</input>
<output>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>1280</dim>
</port>
</output>
</layer>
<layer id="30" name="LSTMSequence_52" type="LSTMSequence" version="opset5">
<data direction="forward" hidden_size="320" activations="sigmoid, tanh, tanh" activations_alpha="" activations_beta="" clip="0" />
<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>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
<port id="3" precision="I64">
<dim>1</dim>
</port>
<port id="4" precision="FP32">
<dim>1</dim>
<dim>1280</dim>
<dim>320</dim>
</port>
<port id="5" precision="FP32">
<dim>1</dim>
<dim>1280</dim>
<dim>320</dim>
</port>
<port id="6" precision="FP32">
<dim>1</dim>
<dim>1280</dim>
</port>
</input>
<output>
<port id="7" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
<port id="8" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
<port id="9" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="31" name="Constant_1949" type="Const" version="opset1">
<data element_type="i64" shape="3" offset="2297008" size="24" />
<rt_info>
<attribute name="precise" version="0" />
</rt_info>
<output>
<port id="0" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="32" name="c" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
<port id="1" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="c">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="34" name="Constant_1951" type="Const" version="opset1">
<data element_type="i64" shape="3" offset="2297008" size="24" />
<rt_info>
<attribute name="precise" version="0" />
</rt_info>
<output>
<port id="0" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="35" name="h" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
<port id="1" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="h">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="37" name="Constant_1942" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="656032" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="38" name="dec" type="Squeeze" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<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="dec">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</output>
</layer>
<layer id="39" name="dec/sink_port_0" type="Result" version="opset1" output_names="dec">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</input>
</layer>
<layer id="36" name="h/sink_port_0" type="Result" version="opset1" output_names="h">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</input>
</layer>
<layer id="33" name="c/sink_port_0" type="Result" version="opset1" output_names="c">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>1</dim>
<dim>320</dim>
</port>
</input>
</layer>
</layers>
<edges>
<edge from-layer="0" from-port="0" to-layer="10" 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="6" to-port="1" />
<edge from-layer="2" from-port="0" to-layer="11" to-port="0" />
<edge from-layer="3" from-port="0" to-layer="4" to-port="0" />
<edge from-layer="4" from-port="1" to-layer="6" to-port="0" />
<edge from-layer="4" from-port="1" to-layer="12" to-port="0" />
<edge from-layer="5" from-port="0" to-layer="6" to-port="2" />
<edge from-layer="6" from-port="3" to-layer="30" 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="30" to-port="1" />
<edge from-layer="9" from-port="0" to-layer="10" to-port="1" />
<edge from-layer="10" from-port="2" to-layer="30" to-port="2" />
<edge from-layer="11" from-port="1" to-layer="16" to-port="0" />
<edge from-layer="12" from-port="1" to-layer="15" to-port="0" />
<edge from-layer="13" from-port="0" to-layer="15" to-port="1" />
<edge from-layer="14" from-port="0" to-layer="15" to-port="2" />
<edge from-layer="15" from-port="3" to-layer="16" to-port="1" />
<edge from-layer="16" from-port="2" to-layer="19" to-port="0" />
<edge from-layer="16" from-port="2" to-layer="22" 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="23" 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="30" to-port="3" />
<edge from-layer="24" from-port="0" to-layer="25" to-port="0" />
<edge from-layer="25" from-port="1" to-layer="30" to-port="4" />
<edge from-layer="26" from-port="0" to-layer="27" to-port="0" />
<edge from-layer="27" from-port="1" to-layer="30" to-port="5" />
<edge from-layer="28" from-port="0" to-layer="29" to-port="0" />
<edge from-layer="29" from-port="1" to-layer="30" to-port="6" />
<edge from-layer="30" from-port="9" to-layer="32" to-port="0" />
<edge from-layer="30" from-port="8" to-layer="35" to-port="0" />
<edge from-layer="30" from-port="7" to-layer="38" to-port="0" />
<edge from-layer="31" from-port="0" to-layer="32" to-port="1" />
<edge from-layer="32" from-port="2" to-layer="33" to-port="0" />
<edge from-layer="34" from-port="0" to-layer="35" to-port="1" />
<edge from-layer="35" from-port="2" to-layer="36" to-port="0" />
<edge from-layer="37" from-port="0" to-layer="38" to-port="1" />
<edge from-layer="38" from-port="2" to-layer="39" 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_decoder.onnx" />
<is_python_object value="False" />
</conversion_parameters>
</rt_info>
</net>