Upload 5 files

PldaRho.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0be6ce8767cc572779215d3a442a93b029c39ff34ecee9beb176999555547da2
+size 243

PldaRho.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a06352a5114b37e1e9f5b472a6551b169a263c16d4b7aca43281b3eadbfe1a
+size 525

PldaRho.mlmodelc/metadata.json

@@ -0,0 +1,71 @@
+[
+  {
+    "shortDescription" : "pyannote community-1 PLDA rho (features scaled by sqrt(phi) for VBx clustering)",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 128)",
+        "shortDescription" : "",
+        "shape" : "[1, 128]",
+        "name" : "rho",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "pyannote-speaker-diarization-community-1",
+    "modelParameters" : [
+
+    ],
+    "author" : "Fluid Inference",
+    "specificationVersion" : 8,
+    "storagePrecision" : "Float32",
+    "license" : "CC-BY-4.0",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.reduceSum" : 2,
+      "Ios17.clip" : 2,
+      "Ios17.sqrt" : 2,
+      "Ios17.linear" : 2,
+      "Ios17.realDiv" : 2,
+      "Ios17.mul" : 5,
+      "Ios17.sub" : 3
+    },
+    "computePrecision" : "Mixed (Float32, Int32)",
+    "stateSchema" : [
+
+    ],
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "14.0",
+      "tvOS" : "17.0",
+      "visionOS" : "1.0",
+      "watchOS" : "10.0",
+      "iOS" : "17.0",
+      "macCatalyst" : "17.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 256)",
+        "shortDescription" : "",
+        "shape" : "[1, 256]",
+        "name" : "embeddings",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.conversion_date" : "2025-10-02",
+      "com.github.apple.coremltools.source" : "torch==2.8.0",
+      "com.github.apple.coremltools.version" : "9.0b1",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript"
+    },
+    "generatedClassName" : "plda_rho_community_1",
+    "method" : "predict"
+  }
+]

PldaRho.mlmodelc/model.mil

@@ -0,0 +1,40 @@
+program(1.0)
+[buildInfo = dict<tensor<string, []>, tensor<string, []>>({{"coremlc-component-MIL", "3500.14.1"}, {"coremlc-version", "3500.32.1"}, {"coremltools-component-torch", "2.8.0"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "9.0b1"}})]
+{
+    func main<ios17>(tensor<fp32, [1, 256]> embeddings) {
+            tensor<fp32, [128]> sqrt_phi = const()[name = tensor<string, []>("sqrt_phi"), val = tensor<fp32, [128]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(64)))];
+            tensor<fp32, [128, 128]> transform_plda_tr = const()[name = tensor<string, []>("transform_plda_tr"), val = tensor<fp32, [128, 128]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(640)))];
+            tensor<fp32, [128]> transform_mu = const()[name = tensor<string, []>("transform_mu"), val = tensor<fp32, [128]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(66240)))];
+            tensor<fp32, []> transform_lda_dim_scale = const()[name = tensor<string, []>("transform_lda_dim_scale"), val = tensor<fp32, []>(0x1.6a09e6p+3)];
+            tensor<fp32, [128]> transform_mean2 = const()[name = tensor<string, []>("transform_mean2"), val = tensor<fp32, [128]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(66816)))];
+            tensor<fp32, []> transform_lda_scale = const()[name = tensor<string, []>("transform_lda_scale"), val = tensor<fp32, []>(0x1p+4)];
+            tensor<fp32, [256]> transform_mean1 = const()[name = tensor<string, []>("transform_mean1"), val = tensor<fp32, [256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(67392)))];
+            tensor<fp32, []> var_4 = const()[name = tensor<string, []>("op_4"), val = tensor<fp32, []>(0x1.197998p-40)];
+            tensor<fp32, [1, 256]> x_1 = sub(x = embeddings, y = transform_mean1)[name = tensor<string, []>("x_1")];
+            tensor<fp32, [1, 256]> var_17 = mul(x = x_1, y = x_1)[name = tensor<string, []>("op_17")];
+            tensor<int32, [1]> var_19_axes_0 = const()[name = tensor<string, []>("op_19_axes_0"), val = tensor<int32, [1]>([-1])];
+            tensor<bool, []> var_19_keep_dims_0 = const()[name = tensor<string, []>("op_19_keep_dims_0"), val = tensor<bool, []>(true)];
+            tensor<fp32, [1, 1]> var_19 = reduce_sum(axes = var_19_axes_0, keep_dims = var_19_keep_dims_0, x = var_17)[name = tensor<string, []>("op_19")];
+            tensor<fp32, []> const_0 = const()[name = tensor<string, []>("const_0"), val = tensor<fp32, []>(0x1.fffffep+127)];
+            tensor<fp32, [1, 1]> clip_0 = clip(alpha = var_4, beta = const_0, x = var_19)[name = tensor<string, []>("clip_0")];
+            tensor<fp32, [1, 1]> norm_1 = sqrt(x = clip_0)[name = tensor<string, []>("norm_1")];
+            tensor<fp32, [1, 256]> normalized1 = real_div(x = x_1, y = norm_1)[name = tensor<string, []>("normalized1")];
+            tensor<fp32, [128, 256]> transpose_0 = const()[name = tensor<string, []>("transpose_0"), val = tensor<fp32, [128, 256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(68480)))];
+            tensor<fp32, [128]> var_23_bias_0 = const()[name = tensor<string, []>("op_23_bias_0"), val = tensor<fp32, [128]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(199616)))];
+            tensor<fp32, [1, 128]> var_23 = linear(bias = var_23_bias_0, weight = transpose_0, x = normalized1)[name = tensor<string, []>("op_23")];
+            tensor<fp32, [1, 128]> projected = mul(x = var_23, y = transform_lda_scale)[name = tensor<string, []>("projected")];
+            tensor<fp32, [1, 128]> x = sub(x = projected, y = transform_mean2)[name = tensor<string, []>("x")];
+            tensor<fp32, [1, 128]> var_26 = mul(x = x, y = x)[name = tensor<string, []>("op_26")];
+            tensor<int32, [1]> var_28_axes_0 = const()[name = tensor<string, []>("op_28_axes_0"), val = tensor<int32, [1]>([-1])];
+            tensor<bool, []> var_28_keep_dims_0 = const()[name = tensor<string, []>("op_28_keep_dims_0"), val = tensor<bool, []>(true)];
+            tensor<fp32, [1, 1]> var_28 = reduce_sum(axes = var_28_axes_0, keep_dims = var_28_keep_dims_0, x = var_26)[name = tensor<string, []>("op_28")];
+            tensor<fp32, []> const_1 = const()[name = tensor<string, []>("const_1"), val = tensor<fp32, []>(0x1.fffffep+127)];
+            tensor<fp32, [1, 1]> clip_1 = clip(alpha = var_4, beta = const_1, x = var_28)[name = tensor<string, []>("clip_1")];
+            tensor<fp32, [1, 1]> norm = sqrt(x = clip_1)[name = tensor<string, []>("norm")];
+            tensor<fp32, [1, 128]> var_31 = real_div(x = x, y = norm)[name = tensor<string, []>("op_31")];
+            tensor<fp32, [1, 128]> normalized2 = mul(x = var_31, y = transform_lda_dim_scale)[name = tensor<string, []>("normalized2")];
+            tensor<fp32, [1, 128]> plda_centered = sub(x = normalized2, y = transform_mu)[name = tensor<string, []>("plda_centered")];
+            tensor<fp32, [1, 128]> features = linear(bias = var_23_bias_0, weight = transform_plda_tr, x = plda_centered)[name = tensor<string, []>("features")];
+            tensor<fp32, [1, 128]> rho = mul(x = features, y = sqrt_phi)[name = tensor<string, []>("op_36")];
+        } -> (rho);
+}

PldaRho.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80f7d229202636d372428c90596f11a91545f07da77259f07153aaf225914a36
+size 200192