Upload 10 files

pyannote_segmentation.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b379db0541b35344a34bb7540783ae704c11599bbed5aa8bbbda11c20ad215ee
+size 243

pyannote_segmentation.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a450ea1b053b9eb7eef0cab6971018076600840c7e246d064e7c5387f456c98
+size 316

pyannote_segmentation.mlmodelc/metadata.json

@@ -0,0 +1,70 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Mixed (Float16, Float32)",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 589 × 7)",
+        "shortDescription" : "",
+        "shape" : "[1, 589, 7]",
+        "name" : "segments",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 6,
+    "mlProgramOperationTypeHistogram" : {
+      "Abs" : 1,
+      "InstanceNorm" : 4,
+      "Cast" : 4,
+      "Conv" : 3,
+      "MaxPool" : 3,
+      "Lstm" : 4,
+      "Transpose" : 2,
+      "Linear" : 3,
+      "Softmax" : 1,
+      "Log" : 1,
+      "LeakyRelu" : 5
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "isUpdatable" : "0",
+    "stateSchema" : [
+
+    ],
+    "availability" : {
+      "macOS" : "12.0",
+      "tvOS" : "15.0",
+      "visionOS" : "1.0",
+      "watchOS" : "8.0",
+      "iOS" : "15.0",
+      "macCatalyst" : "15.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.6.0",
+      "com.github.apple.coremltools.version" : "8.3.0"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 1 × 160000)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 160000]",
+        "name" : "audio",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "pyannote_segmentation",
+    "method" : "predict"
+  }
+]

pyannote_segmentation.mlmodelc/model.mil

@@ -0,0 +1,143 @@
+program(1.0)
+[buildInfo = dict<tensor<string, []>, tensor<string, []>>({{"coremlc-component-MIL", "3402.3.2"}, {"coremlc-version", "3402.4.1"}, {"coremltools-component-torch", "2.6.0"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "8.3.0"}})]
+{
+    func main<ios15>(tensor<fp32, [1, 1, 160000]> audio) {
+            tensor<string, []> audio_to_fp16_dtype_0 = const()[name = tensor<string, []>("audio_to_fp16_dtype_0"), val = tensor<string, []>("fp16")];
+            tensor<fp16, [1]> sincnet_wav_norm1d_weight_to_fp16 = const()[name = tensor<string, []>("sincnet_wav_norm1d_weight_to_fp16"), val = tensor<fp16, [1]>([0x1.44p-7])];
+            tensor<fp16, [1]> sincnet_wav_norm1d_bias_to_fp16 = const()[name = tensor<string, []>("sincnet_wav_norm1d_bias_to_fp16"), val = tensor<fp16, [1]>([0x1.734p-5])];
+            tensor<fp16, []> var_25_to_fp16 = const()[name = tensor<string, []>("op_25_to_fp16"), val = tensor<fp16, []>(0x1.5p-17)];
+            tensor<fp16, [1, 1, 160000]> audio_to_fp16 = cast(dtype = audio_to_fp16_dtype_0, x = audio)[name = tensor<string, []>("cast_19")];
+            tensor<fp16, [1, 1, 160000]> var_41_cast_fp16 = instance_norm(beta = sincnet_wav_norm1d_bias_to_fp16, epsilon = var_25_to_fp16, gamma = sincnet_wav_norm1d_weight_to_fp16, x = audio_to_fp16)[name = tensor<string, []>("op_41_cast_fp16")];
+            tensor<string, []> outputs_pad_type_0 = const()[name = tensor<string, []>("outputs_pad_type_0"), val = tensor<string, []>("valid")];
+            tensor<int32, [1]> outputs_strides_0 = const()[name = tensor<string, []>("outputs_strides_0"), val = tensor<int32, [1]>([10])];
+            tensor<int32, [2]> outputs_pad_0 = const()[name = tensor<string, []>("outputs_pad_0"), val = tensor<int32, [2]>([0, 0])];
+            tensor<int32, [1]> outputs_dilations_0 = const()[name = tensor<string, []>("outputs_dilations_0"), val = tensor<int32, [1]>([1])];
+            tensor<int32, []> outputs_groups_0 = const()[name = tensor<string, []>("outputs_groups_0"), val = tensor<int32, []>(1)];
+            tensor<fp16, [80, 1, 251]> var_113_to_fp16 = const()[name = tensor<string, []>("op_113_to_fp16"), val = tensor<fp16, [80, 1, 251]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(64)))];
+            tensor<fp16, [1, 80, 15975]> outputs_cast_fp16 = conv(dilations = outputs_dilations_0, groups = outputs_groups_0, pad = outputs_pad_0, pad_type = outputs_pad_type_0, strides = outputs_strides_0, weight = var_113_to_fp16, x = var_41_cast_fp16)[name = tensor<string, []>("outputs_cast_fp16")];
+            tensor<fp16, [1, 80, 15975]> input_1_cast_fp16 = abs(x = outputs_cast_fp16)[name = tensor<string, []>("input_1_cast_fp16")];
+            tensor<int32, [1]> var_118 = const()[name = tensor<string, []>("op_118"), val = tensor<int32, [1]>([3])];
+            tensor<int32, [1]> var_119 = const()[name = tensor<string, []>("op_119"), val = tensor<int32, [1]>([3])];
+            tensor<string, []> input_3_pad_type_0 = const()[name = tensor<string, []>("input_3_pad_type_0"), val = tensor<string, []>("custom")];
+            tensor<int32, [2]> input_3_pad_0 = const()[name = tensor<string, []>("input_3_pad_0"), val = tensor<int32, [2]>([0, 0])];
+            tensor<bool, []> input_3_ceil_mode_0 = const()[name = tensor<string, []>("input_3_ceil_mode_0"), val = tensor<bool, []>(false)];
+            tensor<fp16, [1, 80, 5325]> input_3_cast_fp16 = max_pool(ceil_mode = input_3_ceil_mode_0, kernel_sizes = var_118, pad = input_3_pad_0, pad_type = input_3_pad_type_0, strides = var_119, x = input_1_cast_fp16)[name = tensor<string, []>("input_3_cast_fp16")];
+            tensor<fp16, [80]> sincnet_norm1d_0_weight_to_fp16 = const()[name = tensor<string, []>("sincnet_norm1d_0_weight_to_fp16"), val = tensor<fp16, [80]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(40320)))];
+            tensor<fp16, [80]> sincnet_norm1d_0_bias_to_fp16 = const()[name = tensor<string, []>("sincnet_norm1d_0_bias_to_fp16"), val = tensor<fp16, [80]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(40576)))];
+            tensor<fp16, [1, 80, 5325]> input_5_cast_fp16 = instance_norm(beta = sincnet_norm1d_0_bias_to_fp16, epsilon = var_25_to_fp16, gamma = sincnet_norm1d_0_weight_to_fp16, x = input_3_cast_fp16)[name = tensor<string, []>("input_5_cast_fp16")];
+            tensor<fp16, []> var_9_to_fp16 = const()[name = tensor<string, []>("op_9_to_fp16"), val = tensor<fp16, []>(0x1.47cp-7)];
+            tensor<fp16, [1, 80, 5325]> input_7_cast_fp16 = leaky_relu(alpha = var_9_to_fp16, x = input_5_cast_fp16)[name = tensor<string, []>("input_7_cast_fp16")];
+            tensor<string, []> input_9_pad_type_0 = const()[name = tensor<string, []>("input_9_pad_type_0"), val = tensor<string, []>("valid")];
+            tensor<int32, [1]> input_9_strides_0 = const()[name = tensor<string, []>("input_9_strides_0"), val = tensor<int32, [1]>([1])];
+            tensor<int32, [2]> input_9_pad_0 = const()[name = tensor<string, []>("input_9_pad_0"), val = tensor<int32, [2]>([0, 0])];
+            tensor<int32, [1]> input_9_dilations_0 = const()[name = tensor<string, []>("input_9_dilations_0"), val = tensor<int32, [1]>([1])];
+            tensor<int32, []> input_9_groups_0 = const()[name = tensor<string, []>("input_9_groups_0"), val = tensor<int32, []>(1)];
+            tensor<fp16, [60, 80, 5]> sincnet_conv1d_1_weight_to_fp16 = const()[name = tensor<string, []>("sincnet_conv1d_1_weight_to_fp16"), val = tensor<fp16, [60, 80, 5]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(40832)))];
+            tensor<fp16, [60]> sincnet_conv1d_1_bias_to_fp16 = const()[name = tensor<string, []>("sincnet_conv1d_1_bias_to_fp16"), val = tensor<fp16, [60]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(88896)))];
+            tensor<fp16, [1, 60, 5321]> input_9_cast_fp16 = conv(bias = sincnet_conv1d_1_bias_to_fp16, dilations = input_9_dilations_0, groups = input_9_groups_0, pad = input_9_pad_0, pad_type = input_9_pad_type_0, strides = input_9_strides_0, weight = sincnet_conv1d_1_weight_to_fp16, x = input_7_cast_fp16)[name = tensor<string, []>("input_9_cast_fp16")];
+            tensor<int32, [1]> var_134 = const()[name = tensor<string, []>("op_134"), val = tensor<int32, [1]>([3])];
+            tensor<int32, [1]> var_135 = const()[name = tensor<string, []>("op_135"), val = tensor<int32, [1]>([3])];
+            tensor<string, []> input_11_pad_type_0 = const()[name = tensor<string, []>("input_11_pad_type_0"), val = tensor<string, []>("custom")];
+            tensor<int32, [2]> input_11_pad_0 = const()[name = tensor<string, []>("input_11_pad_0"), val = tensor<int32, [2]>([0, 0])];
+            tensor<bool, []> input_11_ceil_mode_0 = const()[name = tensor<string, []>("input_11_ceil_mode_0"), val = tensor<bool, []>(false)];
+            tensor<fp16, [1, 60, 1773]> input_11_cast_fp16 = max_pool(ceil_mode = input_11_ceil_mode_0, kernel_sizes = var_134, pad = input_11_pad_0, pad_type = input_11_pad_type_0, strides = var_135, x = input_9_cast_fp16)[name = tensor<string, []>("input_11_cast_fp16")];
+            tensor<fp16, [60]> sincnet_norm1d_1_weight_to_fp16 = const()[name = tensor<string, []>("sincnet_norm1d_1_weight_to_fp16"), val = tensor<fp16, [60]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(89088)))];
+            tensor<fp16, [60]> sincnet_norm1d_1_bias_to_fp16 = const()[name = tensor<string, []>("sincnet_norm1d_1_bias_to_fp16"), val = tensor<fp16, [60]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(89280)))];
+            tensor<fp16, [1, 60, 1773]> input_13_cast_fp16 = instance_norm(beta = sincnet_norm1d_1_bias_to_fp16, epsilon = var_25_to_fp16, gamma = sincnet_norm1d_1_weight_to_fp16, x = input_11_cast_fp16)[name = tensor<string, []>("input_13_cast_fp16")];
+            tensor<fp16, [1, 60, 1773]> input_15_cast_fp16 = leaky_relu(alpha = var_9_to_fp16, x = input_13_cast_fp16)[name = tensor<string, []>("input_15_cast_fp16")];
+            tensor<string, []> input_17_pad_type_0 = const()[name = tensor<string, []>("input_17_pad_type_0"), val = tensor<string, []>("valid")];
+            tensor<int32, [1]> input_17_strides_0 = const()[name = tensor<string, []>("input_17_strides_0"), val = tensor<int32, [1]>([1])];
+            tensor<int32, [2]> input_17_pad_0 = const()[name = tensor<string, []>("input_17_pad_0"), val = tensor<int32, [2]>([0, 0])];
+            tensor<int32, [1]> input_17_dilations_0 = const()[name = tensor<string, []>("input_17_dilations_0"), val = tensor<int32, [1]>([1])];
+            tensor<int32, []> input_17_groups_0 = const()[name = tensor<string, []>("input_17_groups_0"), val = tensor<int32, []>(1)];
+            tensor<fp16, [60, 60, 5]> sincnet_conv1d_2_weight_to_fp16 = const()[name = tensor<string, []>("sincnet_conv1d_2_weight_to_fp16"), val = tensor<fp16, [60, 60, 5]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(89472)))];
+            tensor<fp16, [60]> sincnet_conv1d_2_bias_to_fp16 = const()[name = tensor<string, []>("sincnet_conv1d_2_bias_to_fp16"), val = tensor<fp16, [60]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(125568)))];
+            tensor<fp16, [1, 60, 1769]> input_17_cast_fp16 = conv(bias = sincnet_conv1d_2_bias_to_fp16, dilations = input_17_dilations_0, groups = input_17_groups_0, pad = input_17_pad_0, pad_type = input_17_pad_type_0, strides = input_17_strides_0, weight = sincnet_conv1d_2_weight_to_fp16, x = input_15_cast_fp16)[name = tensor<string, []>("input_17_cast_fp16")];
+            tensor<int32, [1]> var_150 = const()[name = tensor<string, []>("op_150"), val = tensor<int32, [1]>([3])];
+            tensor<int32, [1]> var_151 = const()[name = tensor<string, []>("op_151"), val = tensor<int32, [1]>([3])];
+            tensor<string, []> input_19_pad_type_0 = const()[name = tensor<string, []>("input_19_pad_type_0"), val = tensor<string, []>("custom")];
+            tensor<int32, [2]> input_19_pad_0 = const()[name = tensor<string, []>("input_19_pad_0"), val = tensor<int32, [2]>([0, 0])];
+            tensor<bool, []> input_19_ceil_mode_0 = const()[name = tensor<string, []>("input_19_ceil_mode_0"), val = tensor<bool, []>(false)];
+            tensor<fp16, [1, 60, 589]> input_19_cast_fp16 = max_pool(ceil_mode = input_19_ceil_mode_0, kernel_sizes = var_150, pad = input_19_pad_0, pad_type = input_19_pad_type_0, strides = var_151, x = input_17_cast_fp16)[name = tensor<string, []>("input_19_cast_fp16")];
+            tensor<fp16, [60]> sincnet_norm1d_2_weight_to_fp16 = const()[name = tensor<string, []>("sincnet_norm1d_2_weight_to_fp16"), val = tensor<fp16, [60]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(125760)))];
+            tensor<fp16, [60]> sincnet_norm1d_2_bias_to_fp16 = const()[name = tensor<string, []>("sincnet_norm1d_2_bias_to_fp16"), val = tensor<fp16, [60]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(125952)))];
+            tensor<fp16, [1, 60, 589]> input_21_cast_fp16 = instance_norm(beta = sincnet_norm1d_2_bias_to_fp16, epsilon = var_25_to_fp16, gamma = sincnet_norm1d_2_weight_to_fp16, x = input_19_cast_fp16)[name = tensor<string, []>("input_21_cast_fp16")];
+            tensor<fp16, [1, 60, 589]> x_cast_fp16 = leaky_relu(alpha = var_9_to_fp16, x = input_21_cast_fp16)[name = tensor<string, []>("x_cast_fp16")];
+            tensor<int32, [3]> transpose_4_perm_0 = const()[name = tensor<string, []>("transpose_4_perm_0"), val = tensor<int32, [3]>([2, 0, 1])];
+            tensor<string, []> transpose_4_cast_fp16_to_fp32_dtype_0 = const()[name = tensor<string, []>("transpose_4_cast_fp16_to_fp32_dtype_0"), val = tensor<string, []>("fp32")];
+            tensor<fp32, [512]> add_0 = const()[name = tensor<string, []>("add_0"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(126144)))];
+            tensor<fp32, [512]> add_1 = const()[name = tensor<string, []>("add_1"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(128256)))];
+            tensor<fp32, [512, 60]> concat_4 = const()[name = tensor<string, []>("concat_4"), val = tensor<fp32, [512, 60]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(130368)))];
+            tensor<fp32, [512, 128]> concat_5 = const()[name = tensor<string, []>("concat_5"), val = tensor<fp32, [512, 128]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(253312)))];
+            tensor<fp32, [512, 60]> concat_6 = const()[name = tensor<string, []>("concat_6"), val = tensor<fp32, [512, 60]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(515520)))];
+            tensor<fp32, [512, 128]> concat_7 = const()[name = tensor<string, []>("concat_7"), val = tensor<fp32, [512, 128]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(638464)))];
+            tensor<fp32, [1, 256]> input_25_lstm_layer_0_lstm_h0_reshaped = const()[name = tensor<string, []>("input_25_lstm_layer_0_lstm_h0_reshaped"), val = tensor<fp32, [1, 256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(900672)))];
+            tensor<string, []> input_25_lstm_layer_0_direction_0 = const()[name = tensor<string, []>("input_25_lstm_layer_0_direction_0"), val = tensor<string, []>("bidirectional")];
+            tensor<bool, []> input_25_lstm_layer_0_output_sequence_0 = const()[name = tensor<string, []>("input_25_lstm_layer_0_output_sequence_0"), val = tensor<bool, []>(true)];
+            tensor<string, []> input_25_lstm_layer_0_recurrent_activation_0 = const()[name = tensor<string, []>("input_25_lstm_layer_0_recurrent_activation_0"), val = tensor<string, []>("sigmoid")];
+            tensor<string, []> input_25_lstm_layer_0_cell_activation_0 = const()[name = tensor<string, []>("input_25_lstm_layer_0_cell_activation_0"), val = tensor<string, []>("tanh")];
+            tensor<string, []> input_25_lstm_layer_0_activation_0 = const()[name = tensor<string, []>("input_25_lstm_layer_0_activation_0"), val = tensor<string, []>("tanh")];
+            tensor<fp16, [589, 1, 60]> transpose_4_cast_fp16 = transpose(perm = transpose_4_perm_0, x = x_cast_fp16)[name = tensor<string, []>("transpose_6")];
+            tensor<fp32, [589, 1, 60]> transpose_4_cast_fp16_to_fp32 = cast(dtype = transpose_4_cast_fp16_to_fp32_dtype_0, x = transpose_4_cast_fp16)[name = tensor<string, []>("cast_18")];
+            tensor<fp32, [589, 1, 256]> input_25_lstm_layer_0_0, tensor<fp32, [1, 256]> input_25_lstm_layer_0_1, tensor<fp32, [1, 256]> input_25_lstm_layer_0_2 = lstm(activation = input_25_lstm_layer_0_activation_0, bias = add_0, bias_back = add_1, cell_activation = input_25_lstm_layer_0_cell_activation_0, direction = input_25_lstm_layer_0_direction_0, initial_c = input_25_lstm_layer_0_lstm_h0_reshaped, initial_h = input_25_lstm_layer_0_lstm_h0_reshaped, output_sequence = input_25_lstm_layer_0_output_sequence_0, recurrent_activation = input_25_lstm_layer_0_recurrent_activation_0, weight_hh = concat_5, weight_hh_back = concat_7, weight_ih = concat_4, weight_ih_back = concat_6, x = transpose_4_cast_fp16_to_fp32)[name = tensor<string, []>("input_25_lstm_layer_0")];
+            tensor<fp32, [512]> add_2 = const()[name = tensor<string, []>("add_2"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(901760)))];
+            tensor<fp32, [512]> add_3 = const()[name = tensor<string, []>("add_3"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(903872)))];
+            tensor<fp32, [512, 256]> concat_14 = const()[name = tensor<string, []>("concat_14"), val = tensor<fp32, [512, 256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(905984)))];
+            tensor<fp32, [512, 128]> concat_15 = const()[name = tensor<string, []>("concat_15"), val = tensor<fp32, [512, 128]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(1430336)))];
+            tensor<fp32, [512, 256]> concat_16 = const()[name = tensor<string, []>("concat_16"), val = tensor<fp32, [512, 256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(1692544)))];
+            tensor<fp32, [512, 128]> concat_17 = const()[name = tensor<string, []>("concat_17"), val = tensor<fp32, [512, 128]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(2216896)))];
+            tensor<string, []> input_25_lstm_layer_1_direction_0 = const()[name = tensor<string, []>("input_25_lstm_layer_1_direction_0"), val = tensor<string, []>("bidirectional")];
+            tensor<bool, []> input_25_lstm_layer_1_output_sequence_0 = const()[name = tensor<string, []>("input_25_lstm_layer_1_output_sequence_0"), val = tensor<bool, []>(true)];
+            tensor<string, []> input_25_lstm_layer_1_recurrent_activation_0 = const()[name = tensor<string, []>("input_25_lstm_layer_1_recurrent_activation_0"), val = tensor<string, []>("sigmoid")];
+            tensor<string, []> input_25_lstm_layer_1_cell_activation_0 = const()[name = tensor<string, []>("input_25_lstm_layer_1_cell_activation_0"), val = tensor<string, []>("tanh")];
+            tensor<string, []> input_25_lstm_layer_1_activation_0 = const()[name = tensor<string, []>("input_25_lstm_layer_1_activation_0"), val = tensor<string, []>("tanh")];
+            tensor<fp32, [589, 1, 256]> input_25_lstm_layer_1_0, tensor<fp32, [1, 256]> input_25_lstm_layer_1_1, tensor<fp32, [1, 256]> input_25_lstm_layer_1_2 = lstm(activation = input_25_lstm_layer_1_activation_0, bias = add_2, bias_back = add_3, cell_activation = input_25_lstm_layer_1_cell_activation_0, direction = input_25_lstm_layer_1_direction_0, initial_c = input_25_lstm_layer_0_lstm_h0_reshaped, initial_h = input_25_lstm_layer_0_lstm_h0_reshaped, output_sequence = input_25_lstm_layer_1_output_sequence_0, recurrent_activation = input_25_lstm_layer_1_recurrent_activation_0, weight_hh = concat_15, weight_hh_back = concat_17, weight_ih = concat_14, weight_ih_back = concat_16, x = input_25_lstm_layer_0_0)[name = tensor<string, []>("input_25_lstm_layer_1")];
+            tensor<fp32, [512]> add_4 = const()[name = tensor<string, []>("add_4"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(2479104)))];
+            tensor<fp32, [512]> add_5 = const()[name = tensor<string, []>("add_5"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(2481216)))];
+            tensor<fp32, [512, 256]> concat_24 = const()[name = tensor<string, []>("concat_24"), val = tensor<fp32, [512, 256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(2483328)))];
+            tensor<fp32, [512, 128]> concat_25 = const()[name = tensor<string, []>("concat_25"), val = tensor<fp32, [512, 128]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(3007680)))];
+            tensor<fp32, [512, 256]> concat_26 = const()[name = tensor<string, []>("concat_26"), val = tensor<fp32, [512, 256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(3269888)))];
+            tensor<fp32, [512, 128]> concat_27 = const()[name = tensor<string, []>("concat_27"), val = tensor<fp32, [512, 128]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(3794240)))];
+            tensor<string, []> input_25_lstm_layer_2_direction_0 = const()[name = tensor<string, []>("input_25_lstm_layer_2_direction_0"), val = tensor<string, []>("bidirectional")];
+            tensor<bool, []> input_25_lstm_layer_2_output_sequence_0 = const()[name = tensor<string, []>("input_25_lstm_layer_2_output_sequence_0"), val = tensor<bool, []>(true)];
+            tensor<string, []> input_25_lstm_layer_2_recurrent_activation_0 = const()[name = tensor<string, []>("input_25_lstm_layer_2_recurrent_activation_0"), val = tensor<string, []>("sigmoid")];
+            tensor<string, []> input_25_lstm_layer_2_cell_activation_0 = const()[name = tensor<string, []>("input_25_lstm_layer_2_cell_activation_0"), val = tensor<string, []>("tanh")];
+            tensor<string, []> input_25_lstm_layer_2_activation_0 = const()[name = tensor<string, []>("input_25_lstm_layer_2_activation_0"), val = tensor<string, []>("tanh")];
+            tensor<fp32, [589, 1, 256]> input_25_lstm_layer_2_0, tensor<fp32, [1, 256]> input_25_lstm_layer_2_1, tensor<fp32, [1, 256]> input_25_lstm_layer_2_2 = lstm(activation = input_25_lstm_layer_2_activation_0, bias = add_4, bias_back = add_5, cell_activation = input_25_lstm_layer_2_cell_activation_0, direction = input_25_lstm_layer_2_direction_0, initial_c = input_25_lstm_layer_0_lstm_h0_reshaped, initial_h = input_25_lstm_layer_0_lstm_h0_reshaped, output_sequence = input_25_lstm_layer_2_output_sequence_0, recurrent_activation = input_25_lstm_layer_2_recurrent_activation_0, weight_hh = concat_25, weight_hh_back = concat_27, weight_ih = concat_24, weight_ih_back = concat_26, x = input_25_lstm_layer_1_0)[name = tensor<string, []>("input_25_lstm_layer_2")];
+            tensor<fp32, [512]> add_6 = const()[name = tensor<string, []>("add_6"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(4056448)))];
+            tensor<fp32, [512]> add_7 = const()[name = tensor<string, []>("add_7"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(4058560)))];
+            tensor<fp32, [512, 256]> concat_34 = const()[name = tensor<string, []>("concat_34"), val = tensor<fp32, [512, 256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(4060672)))];
+            tensor<fp32, [512, 128]> concat_35 = const()[name = tensor<string, []>("concat_35"), val = tensor<fp32, [512, 128]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(4585024)))];
+            tensor<fp32, [512, 256]> concat_36 = const()[name = tensor<string, []>("concat_36"), val = tensor<fp32, [512, 256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(4847232)))];
+            tensor<fp32, [512, 128]> concat_37 = const()[name = tensor<string, []>("concat_37"), val = tensor<fp32, [512, 128]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(5371584)))];
+            tensor<string, []> input_25_batch_first_direction_0 = const()[name = tensor<string, []>("input_25_batch_first_direction_0"), val = tensor<string, []>("bidirectional")];
+            tensor<bool, []> input_25_batch_first_output_sequence_0 = const()[name = tensor<string, []>("input_25_batch_first_output_sequence_0"), val = tensor<bool, []>(true)];
+            tensor<string, []> input_25_batch_first_recurrent_activation_0 = const()[name = tensor<string, []>("input_25_batch_first_recurrent_activation_0"), val = tensor<string, []>("sigmoid")];
+            tensor<string, []> input_25_batch_first_cell_activation_0 = const()[name = tensor<string, []>("input_25_batch_first_cell_activation_0"), val = tensor<string, []>("tanh")];
+            tensor<string, []> input_25_batch_first_activation_0 = const()[name = tensor<string, []>("input_25_batch_first_activation_0"), val = tensor<string, []>("tanh")];
+            tensor<fp32, [589, 1, 256]> input_25_batch_first_0, tensor<fp32, [1, 256]> input_25_batch_first_1, tensor<fp32, [1, 256]> input_25_batch_first_2 = lstm(activation = input_25_batch_first_activation_0, bias = add_6, bias_back = add_7, cell_activation = input_25_batch_first_cell_activation_0, direction = input_25_batch_first_direction_0, initial_c = input_25_lstm_layer_0_lstm_h0_reshaped, initial_h = input_25_lstm_layer_0_lstm_h0_reshaped, output_sequence = input_25_batch_first_output_sequence_0, recurrent_activation = input_25_batch_first_recurrent_activation_0, weight_hh = concat_35, weight_hh_back = concat_37, weight_ih = concat_34, weight_ih_back = concat_36, x = input_25_lstm_layer_2_0)[name = tensor<string, []>("input_25_batch_first")];
+            tensor<int32, [3]> input_25_perm_0 = const()[name = tensor<string, []>("input_25_perm_0"), val = tensor<int32, [3]>([1, 0, 2])];
+            tensor<string, []> input_25_batch_first_0_to_fp16_dtype_0 = const()[name = tensor<string, []>("input_25_batch_first_0_to_fp16_dtype_0"), val = tensor<string, []>("fp16")];
+            tensor<fp16, [128, 256]> linear_0_weight_to_fp16 = const()[name = tensor<string, []>("linear_0_weight_to_fp16"), val = tensor<fp16, [128, 256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(5633792)))];
+            tensor<fp16, [128]> linear_0_bias_to_fp16 = const()[name = tensor<string, []>("linear_0_bias_to_fp16"), val = tensor<fp16, [128]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(5699392)))];
+            tensor<fp16, [589, 1, 256]> input_25_batch_first_0_to_fp16 = cast(dtype = input_25_batch_first_0_to_fp16_dtype_0, x = input_25_batch_first_0)[name = tensor<string, []>("cast_17")];
+            tensor<fp16, [1, 589, 256]> input_25_cast_fp16 = transpose(perm = input_25_perm_0, x = input_25_batch_first_0_to_fp16)[name = tensor<string, []>("transpose_5")];
+            tensor<fp16, [1, 589, 128]> linear_0_cast_fp16 = linear(bias = linear_0_bias_to_fp16, weight = linear_0_weight_to_fp16, x = input_25_cast_fp16)[name = tensor<string, []>("linear_0_cast_fp16")];
+            tensor<fp16, []> var_219_to_fp16 = const()[name = tensor<string, []>("op_219_to_fp16"), val = tensor<fp16, []>(0x1.47cp-7)];
+            tensor<fp16, [1, 589, 128]> input_29_cast_fp16 = leaky_relu(alpha = var_219_to_fp16, x = linear_0_cast_fp16)[name = tensor<string, []>("input_29_cast_fp16")];
+            tensor<fp16, [128, 128]> linear_1_weight_to_fp16 = const()[name = tensor<string, []>("linear_1_weight_to_fp16"), val = tensor<fp16, [128, 128]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(5699712)))];
+            tensor<fp16, [128]> linear_1_bias_to_fp16 = const()[name = tensor<string, []>("linear_1_bias_to_fp16"), val = tensor<fp16, [128]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(5732544)))];
+            tensor<fp16, [1, 589, 128]> linear_1_cast_fp16 = linear(bias = linear_1_bias_to_fp16, weight = linear_1_weight_to_fp16, x = input_29_cast_fp16)[name = tensor<string, []>("linear_1_cast_fp16")];
+            tensor<fp16, []> var_224_to_fp16 = const()[name = tensor<string, []>("op_224_to_fp16"), val = tensor<fp16, []>(0x1.47cp-7)];
+            tensor<fp16, [1, 589, 128]> input_33_cast_fp16 = leaky_relu(alpha = var_224_to_fp16, x = linear_1_cast_fp16)[name = tensor<string, []>("input_33_cast_fp16")];
+            tensor<fp16, [7, 128]> classifier_weight_to_fp16 = const()[name = tensor<string, []>("classifier_weight_to_fp16"), val = tensor<fp16, [7, 128]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(5732864)))];
+            tensor<fp16, [7]> classifier_bias_to_fp16 = const()[name = tensor<string, []>("classifier_bias_to_fp16"), val = tensor<fp16, [7]>([-0x1.01p+0, 0x1.67cp-2, 0x1.3d8p-1, 0x1.c8cp-2, -0x1.444p-2, -0x1.59p-1, -0x1.8fcp-2])];
+            tensor<fp16, [1, 589, 7]> linear_2_cast_fp16 = linear(bias = classifier_bias_to_fp16, weight = classifier_weight_to_fp16, x = input_33_cast_fp16)[name = tensor<string, []>("linear_2_cast_fp16")];
+            tensor<int32, []> var_230 = const()[name = tensor<string, []>("op_230"), val = tensor<int32, []>(-1)];
+            tensor<fp16, [1, 589, 7]> var_231_softmax_cast_fp16 = softmax(axis = var_230, x = linear_2_cast_fp16)[name = tensor<string, []>("op_231_softmax_cast_fp16")];
+            tensor<fp16, []> var_231_epsilon_0_to_fp16 = const()[name = tensor<string, []>("op_231_epsilon_0_to_fp16"), val = tensor<fp16, []>(0x0p+0)];
+            tensor<fp16, [1, 589, 7]> var_231_cast_fp16 = log(epsilon = var_231_epsilon_0_to_fp16, x = var_231_softmax_cast_fp16)[name = tensor<string, []>("op_231_cast_fp16")];
+            tensor<string, []> var_231_cast_fp16_to_fp32_dtype_0 = const()[name = tensor<string, []>("op_231_cast_fp16_to_fp32_dtype_0"), val = tensor<string, []>("fp32")];
+            tensor<fp32, [1, 589, 7]> segments = cast(dtype = var_231_cast_fp16_to_fp32_dtype_0, x = var_231_cast_fp16)[name = tensor<string, []>("cast_16")];
+        } -> (segments);
+}

pyannote_segmentation.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0266f4ad4d843ecf31ef9220ad6b80616b3ec64a4404b64f3ea0371554e236ec
+size 5734720

wespeaker.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f79ae5563cd4807a2e10630ce8aac7bdc469e37d7c723acce06f54df75c1f21
+size 243

wespeaker.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dcd845627ea84f3f764e48b8ed3c2a14b593bab94045377bf7662add50e2972
+size 359

wespeaker.mlmodelc/metadata.json

@@ -0,0 +1,104 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Float32",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32)",
+        "shortDescription" : "",
+        "shape" : "[]",
+        "name" : "constant",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 3 × 256)",
+        "shortDescription" : "",
+        "shape" : "[3, 256]",
+        "name" : "embedding",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 6,
+    "mlProgramOperationTypeHistogram" : {
+      "Transpose" : 4,
+      "Square" : 2,
+      "UpsampleNearestNeighbor" : 1,
+      "Squeeze" : 5,
+      "Sub" : 5,
+      "ReduceMean" : 2,
+      "Gather" : 2,
+      "Identity" : 1,
+      "Reshape" : 1,
+      "Matmul" : 2,
+      "Concat" : 1,
+      "Add" : 19,
+      "Sqrt" : 1,
+      "RealDiv" : 3,
+      "Pad" : 2,
+      "Linear" : 2,
+      "Relu" : 33,
+      "ExpandDims" : 11,
+      "Conv" : 36,
+      "Maximum" : 1,
+      "Log" : 1,
+      "SliceByIndex" : 1001,
+      "Stack" : 1,
+      "ReduceSum" : 4,
+      "Mul" : 8
+    },
+    "computePrecision" : "Mixed (Float32, Int32)",
+    "isUpdatable" : "0",
+    "stateSchema" : [
+
+    ],
+    "availability" : {
+      "macOS" : "12.0",
+      "tvOS" : "15.0",
+      "visionOS" : "1.0",
+      "watchOS" : "8.0",
+      "iOS" : "15.0",
+      "macCatalyst" : "15.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.6.0",
+      "com.github.apple.coremltools.version" : "8.3.0"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 3 × 160000)",
+        "shortDescription" : "",
+        "shape" : "[3, 160000]",
+        "name" : "waveform",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 3 × 589)",
+        "shortDescription" : "",
+        "shape" : "[3, 589]",
+        "name" : "mask",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "wespeaker",
+    "method" : "predict"
+  }
+]

wespeaker.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:680837ec172d67c3197bba93800e1623eebfd35c3b17011802f5f98b8026a0aa
+size 28706752