{ "source_onnx": "KittenML/kitten-tts-mini-0.8:kitten_tts_mini_v0_8.onnx", "opset": [ [ "", 20 ], [ "ai.onnx.ml", 5 ], [ "ai.onnx.training", 1 ], [ "ai.onnx.preview.training", 1 ], [ "com.microsoft", 1 ], [ "com.microsoft.experimental", 1 ], [ "com.microsoft.nchwc", 1 ], [ "org.pytorch.aten", 1 ] ], "inputs": [ { "name": "input_ids", "shape": [ 1, "sequence_length" ], "dtype": "i64" }, { "name": "style", "shape": [ 1, 256 ], "dtype": "f32" }, { "name": "speed", "shape": [ 1 ], "dtype": "f32" } ], "outputs": [ { "name": "waveform", "shape": [ "num_samples" ], "dtype": "f32" }, { "name": "duration", "shape": [ "Castduration_dim_0" ], "dtype": "i64" } ], "node_count": 3006, "initializer_count": 1140, "op_histogram": { "SequenceEmpty": 1, "Shape": 88, "Gather": 148, "Cast": 251, "Reshape": 192, "Slice": 144, "Transpose": 91, "DynamicQuantizeLinear": 125, "Squeeze": 4, "Range": 7, "Unsqueeze": 131, "Mul": 637, "MatMul": 163, "Concat": 77, "ConstantOfShape": 14, "Equal": 12, "Add": 467, "Where": 22, "ReduceMax": 1, "Loop": 1, "Expand": 15, "ConcatFromSequence": 1, "TopK": 1, "ReduceProd": 1, "LayerNormalization": 31, "ScatterElements": 1, "Greater": 3, "Not": 1, "ConvInteger": 74, "ScatterND": 3, "LeakyRelu": 28, "Sub": 5, "Sqrt": 25, "Div": 30, "Softmax": 12, "Pow": 50, "DynamicQuantizeLSTM": 6, "Tanh": 13, "InstanceNormalization": 55, "Sigmoid": 1, "ReduceSum": 1, "Round": 1, "Clip": 1, "SplitToSequence": 2, "Resize": 6, "ConvTranspose": 7, "If": 2, "Conv": 4, "Floor": 1, "RandomUniformLike": 1, "CumSum": 1, "Sin": 39, "RandomNormalLike": 1, "Pad": 2, "Less": 1, "Atan": 1, "And": 1, "Exp": 1, "Cos": 1 } }