|
|
<?xml version="1.0"?> |
|
|
<net name="Model6" version="11"> |
|
|
<layers> |
|
|
<layer id="0" name="raw_spectrogram" type="Parameter" version="opset1"> |
|
|
<data shape="?,?,2,80" element_type="f32" /> |
|
|
<output> |
|
|
<port id="0" precision="FP32" names="raw_spectrogram"> |
|
|
<dim>-1</dim> |
|
|
<dim>-1</dim> |
|
|
<dim>2</dim> |
|
|
<dim>80</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="1" name="aten::transpose/Constant" type="Const" version="opset1"> |
|
|
<data element_type="i32" shape="4" offset="0" size="16" /> |
|
|
<output> |
|
|
<port id="0" precision="I32"> |
|
|
<dim>4</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="2" name="aten::transpose/Transpose" type="Transpose" version="opset1"> |
|
|
<input> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>-1</dim> |
|
|
<dim>-1</dim> |
|
|
<dim>2</dim> |
|
|
<dim>80</dim> |
|
|
</port> |
|
|
<port id="1" precision="I32"> |
|
|
<dim>4</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="2" precision="FP32" names="19"> |
|
|
<dim>-1</dim> |
|
|
<dim>-1</dim> |
|
|
<dim>2</dim> |
|
|
<dim>80</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="3" name="Constant_22093" type="Const" version="opset1"> |
|
|
<data element_type="i32" shape="1" offset="16" size="4" /> |
|
|
<output> |
|
|
<port id="0" precision="I32"> |
|
|
<dim>1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="4" name="aten::flatten/Constant_2" type="Const" version="opset1"> |
|
|
<data element_type="i32" shape="1" offset="20" size="4" /> |
|
|
<output> |
|
|
<port id="0" precision="I32"> |
|
|
<dim>1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="5" name="ShapeOf_21977" type="ShapeOf" version="opset3"> |
|
|
<data output_type="i32" /> |
|
|
<input> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>-1</dim> |
|
|
<dim>-1</dim> |
|
|
<dim>2</dim> |
|
|
<dim>80</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="1" precision="I32"> |
|
|
<dim>4</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="6" name="Constant_21984" type="Const" version="opset1"> |
|
|
<data element_type="i64" shape="1" offset="24" size="8" /> |
|
|
<output> |
|
|
<port id="0" precision="I64"> |
|
|
<dim>1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="7" name="Constant_21985" type="Const" version="opset1"> |
|
|
<data element_type="i64" shape="" offset="32" size="8" /> |
|
|
<output> |
|
|
<port id="0" precision="I64" /> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="8" name="Gather_21986" type="Gather" version="opset8"> |
|
|
<data batch_dims="0" /> |
|
|
<input> |
|
|
<port id="0" precision="I32"> |
|
|
<dim>4</dim> |
|
|
</port> |
|
|
<port id="1" precision="I64"> |
|
|
<dim>1</dim> |
|
|
</port> |
|
|
<port id="2" precision="I64" /> |
|
|
</input> |
|
|
<output> |
|
|
<port id="3" precision="I32"> |
|
|
<dim>1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="9" name="aten::flatten/Concat" type="Concat" version="opset1"> |
|
|
<data axis="0" /> |
|
|
<input> |
|
|
<port id="0" precision="I32"> |
|
|
<dim>1</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="I32"> |
|
|
<dim>3</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="10" 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>2</dim> |
|
|
<dim>80</dim> |
|
|
</port> |
|
|
<port id="1" precision="I32"> |
|
|
<dim>3</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="2" precision="FP32" names="22,hidden_states"> |
|
|
<dim>-1</dim> |
|
|
<dim>-1</dim> |
|
|
<dim>80</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="11" name="aten::transpose/Constant_1" type="Const" version="opset1"> |
|
|
<data element_type="i32" shape="3" offset="40" size="12" /> |
|
|
<output> |
|
|
<port id="0" precision="I32"> |
|
|
<dim>3</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="12" name="aten::transpose/Transpose_1" type="Transpose" version="opset1"> |
|
|
<input> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>-1</dim> |
|
|
<dim>-1</dim> |
|
|
<dim>80</dim> |
|
|
</port> |
|
|
<port id="1" precision="I32"> |
|
|
<dim>3</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="2" precision="FP32" names="25"> |
|
|
<dim>-1</dim> |
|
|
<dim>80</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="13" name="Multiply_21914" type="Const" version="opset1"> |
|
|
<data element_type="f32" shape="256, 80, 5" offset="52" size="409600" /> |
|
|
<output> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>256</dim> |
|
|
<dim>80</dim> |
|
|
<dim>5</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="14" name="Multiply_21877" type="Convolution" version="opset1"> |
|
|
<data strides="1" dilations="1" pads_begin="2" pads_end="2" auto_pad="explicit" /> |
|
|
<input> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>-1</dim> |
|
|
<dim>80</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
<port id="1" precision="FP32"> |
|
|
<dim>256</dim> |
|
|
<dim>80</dim> |
|
|
<dim>5</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="2" precision="FP32" names="60"> |
|
|
<dim>-1</dim> |
|
|
<dim>256</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="15" name="__module.speech_decoder_postnet.layers.0.activation/aten::tanh/Tanh" type="Tanh" version="opset1"> |
|
|
<input> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>-1</dim> |
|
|
<dim>256</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="1" precision="FP32" names="61,input.1"> |
|
|
<dim>-1</dim> |
|
|
<dim>256</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="16" name="Multiply_21918" type="Const" version="opset1"> |
|
|
<data element_type="f32" shape="256, 256, 5" offset="409652" size="1310720" /> |
|
|
<output> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>256</dim> |
|
|
<dim>256</dim> |
|
|
<dim>5</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="17" name="Multiply_21884" type="Convolution" version="opset1"> |
|
|
<data strides="1" dilations="1" pads_begin="2" pads_end="2" auto_pad="explicit" /> |
|
|
<input> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>-1</dim> |
|
|
<dim>256</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
<port id="1" precision="FP32"> |
|
|
<dim>256</dim> |
|
|
<dim>256</dim> |
|
|
<dim>5</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="2" precision="FP32" names="86"> |
|
|
<dim>-1</dim> |
|
|
<dim>256</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="18" name="__module.speech_decoder_postnet.layers.1.activation/aten::tanh/Tanh" type="Tanh" version="opset1"> |
|
|
<input> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>-1</dim> |
|
|
<dim>256</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="1" precision="FP32" names="87,input.3"> |
|
|
<dim>-1</dim> |
|
|
<dim>256</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="19" name="Multiply_21922" type="Const" version="opset1"> |
|
|
<data element_type="f32" shape="256, 256, 5" offset="1720372" size="1310720" /> |
|
|
<output> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>256</dim> |
|
|
<dim>256</dim> |
|
|
<dim>5</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="20" name="Multiply_21891" type="Convolution" version="opset1"> |
|
|
<data strides="1" dilations="1" pads_begin="2" pads_end="2" auto_pad="explicit" /> |
|
|
<input> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>-1</dim> |
|
|
<dim>256</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
<port id="1" precision="FP32"> |
|
|
<dim>256</dim> |
|
|
<dim>256</dim> |
|
|
<dim>5</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="2" precision="FP32" names="112"> |
|
|
<dim>-1</dim> |
|
|
<dim>256</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="21" name="__module.speech_decoder_postnet.layers.2.activation/aten::tanh/Tanh" type="Tanh" version="opset1"> |
|
|
<input> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>-1</dim> |
|
|
<dim>256</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="1" precision="FP32" names="113,input.5"> |
|
|
<dim>-1</dim> |
|
|
<dim>256</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="22" name="Multiply_21926" type="Const" version="opset1"> |
|
|
<data element_type="f32" shape="256, 256, 5" offset="3031092" size="1310720" /> |
|
|
<output> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>256</dim> |
|
|
<dim>256</dim> |
|
|
<dim>5</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="23" name="Multiply_21898" type="Convolution" version="opset1"> |
|
|
<data strides="1" dilations="1" pads_begin="2" pads_end="2" auto_pad="explicit" /> |
|
|
<input> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>-1</dim> |
|
|
<dim>256</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
<port id="1" precision="FP32"> |
|
|
<dim>256</dim> |
|
|
<dim>256</dim> |
|
|
<dim>5</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="2" precision="FP32" names="138"> |
|
|
<dim>-1</dim> |
|
|
<dim>256</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="24" name="__module.speech_decoder_postnet.layers.3.activation/aten::tanh/Tanh" type="Tanh" version="opset1"> |
|
|
<input> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>-1</dim> |
|
|
<dim>256</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="1" precision="FP32" names="139,input.7"> |
|
|
<dim>-1</dim> |
|
|
<dim>256</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="25" name="Multiply_21930" type="Const" version="opset1"> |
|
|
<data element_type="f32" shape="80, 256, 5" offset="4341812" size="409600" /> |
|
|
<output> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>80</dim> |
|
|
<dim>256</dim> |
|
|
<dim>5</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="26" name="Multiply_21905" type="Convolution" version="opset1"> |
|
|
<data strides="1" dilations="1" pads_begin="2" pads_end="2" auto_pad="explicit" /> |
|
|
<input> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>-1</dim> |
|
|
<dim>256</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
<port id="1" precision="FP32"> |
|
|
<dim>80</dim> |
|
|
<dim>256</dim> |
|
|
<dim>5</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="2" precision="FP32" names="163,input"> |
|
|
<dim>-1</dim> |
|
|
<dim>80</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="27" name="aten::transpose/Constant_2" type="Const" version="opset1"> |
|
|
<data element_type="i32" shape="3" offset="40" size="12" /> |
|
|
<output> |
|
|
<port id="0" precision="I32"> |
|
|
<dim>3</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="28" name="aten::transpose/Transpose_2" type="Transpose" version="opset1"> |
|
|
<input> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>-1</dim> |
|
|
<dim>80</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
<port id="1" precision="I32"> |
|
|
<dim>3</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="2" precision="FP32" names="33"> |
|
|
<dim>-1</dim> |
|
|
<dim>-1</dim> |
|
|
<dim>80</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="29" 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>80</dim> |
|
|
</port> |
|
|
<port id="1" precision="FP32"> |
|
|
<dim>-1</dim> |
|
|
<dim>-1</dim> |
|
|
<dim>80</dim> |
|
|
</port> |
|
|
</input> |
|
|
<output> |
|
|
<port id="2" precision="FP32" names="postnet_spectrogram"> |
|
|
<dim>-1</dim> |
|
|
<dim>-1</dim> |
|
|
<dim>80</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="30" name="Result_19725" type="Result" version="opset1" output_names="postnet_spectrogram"> |
|
|
<input> |
|
|
<port id="0" precision="FP32"> |
|
|
<dim>-1</dim> |
|
|
<dim>-1</dim> |
|
|
<dim>80</dim> |
|
|
</port> |
|
|
</input> |
|
|
</layer> |
|
|
</layers> |
|
|
<edges> |
|
|
<edge from-layer="0" from-port="0" to-layer="2" to-port="0" /> |
|
|
<edge from-layer="1" from-port="0" to-layer="2" to-port="1" /> |
|
|
<edge from-layer="2" from-port="2" to-layer="10" to-port="0" /> |
|
|
<edge from-layer="2" from-port="2" to-layer="5" to-port="0" /> |
|
|
<edge from-layer="3" from-port="0" to-layer="9" to-port="0" /> |
|
|
<edge from-layer="4" from-port="0" to-layer="9" to-port="1" /> |
|
|
<edge from-layer="5" from-port="1" to-layer="8" to-port="0" /> |
|
|
<edge from-layer="6" from-port="0" to-layer="8" to-port="1" /> |
|
|
<edge from-layer="7" from-port="0" to-layer="8" to-port="2" /> |
|
|
<edge from-layer="8" from-port="3" to-layer="9" to-port="2" /> |
|
|
<edge from-layer="9" from-port="3" to-layer="10" to-port="1" /> |
|
|
<edge from-layer="10" from-port="2" to-layer="12" to-port="0" /> |
|
|
<edge from-layer="10" from-port="2" to-layer="29" to-port="0" /> |
|
|
<edge from-layer="11" from-port="0" to-layer="12" to-port="1" /> |
|
|
<edge from-layer="12" from-port="2" to-layer="14" to-port="0" /> |
|
|
<edge from-layer="13" from-port="0" to-layer="14" to-port="1" /> |
|
|
<edge from-layer="14" from-port="2" to-layer="15" to-port="0" /> |
|
|
<edge from-layer="15" from-port="1" to-layer="17" to-port="0" /> |
|
|
<edge from-layer="16" from-port="0" to-layer="17" to-port="1" /> |
|
|
<edge from-layer="17" from-port="2" to-layer="18" to-port="0" /> |
|
|
<edge from-layer="18" from-port="1" to-layer="20" to-port="0" /> |
|
|
<edge from-layer="19" from-port="0" 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="23" to-port="0" /> |
|
|
<edge from-layer="22" from-port="0" to-layer="23" to-port="1" /> |
|
|
<edge from-layer="23" from-port="2" to-layer="24" to-port="0" /> |
|
|
<edge from-layer="24" from-port="1" to-layer="26" to-port="0" /> |
|
|
<edge from-layer="25" from-port="0" to-layer="26" to-port="1" /> |
|
|
<edge from-layer="26" from-port="2" to-layer="28" to-port="0" /> |
|
|
<edge from-layer="27" from-port="0" to-layer="28" to-port="1" /> |
|
|
<edge from-layer="28" from-port="2" to-layer="29" to-port="1" /> |
|
|
<edge from-layer="29" from-port="2" to-layer="30" to-port="0" /> |
|
|
</edges> |
|
|
<rt_info> |
|
|
<Runtime_version value="2025.1.0-18503-6fec06580ab-releases/2025/1" /> |
|
|
<conversion_parameters> |
|
|
<framework value="pytorch" /> |
|
|
<is_python_object value="True" /> |
|
|
</conversion_parameters> |
|
|
<optimum> |
|
|
<optimum_intel_version value="1.23.0.dev0+81089b7" /> |
|
|
<optimum_version value="1.25.0.dev0" /> |
|
|
<pytorch_version value="2.5.1+cpu" /> |
|
|
<transformers_version value="4.51.3" /> |
|
|
</optimum> |
|
|
</rt_info> |
|
|
</net> |
|
|
|
