Remove previous version of QLoRA compressed models

openai_whisper-large-v2_1050MB/AudioEncoder.mlmodelc/analytics/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5e279481a1d034396cb8e1f3a0c54f0600fba04b64564a1f219af3fd8305aef9
-size 243

openai_whisper-large-v2_1050MB/AudioEncoder.mlmodelc/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:25208eaf6314ae9bb022b73c7beee053fae9ec462d2a8dadcee60bc9c1289fa3
-size 347

openai_whisper-large-v2_1050MB/AudioEncoder.mlmodelc/metadata.json

@@ -1,68 +0,0 @@
-[
-  {
-    "metadataOutputVersion" : "3.0",
-    "storagePrecision" : "Mixed (Float16, Palettized (4 bits))",
-    "outputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 1280 × 1 × 1500)",
-        "shortDescription" : "",
-        "shape" : "[1, 1280, 1, 1500]",
-        "name" : "encoder_output_embeds",
-        "type" : "MultiArray"
-      }
-    ],
-    "modelParameters" : [
-
-    ],
-    "specificationVersion" : 8,
-    "mlProgramOperationTypeHistogram" : {
-      "Ios17.mul" : 162,
-      "Ios17.rsqrt" : 65,
-      "Ios16.constexprLutToDense" : 177,
-      "Ios17.conv" : 194,
-      "Ios17.matmul" : 64,
-      "Ios17.sub" : 65,
-      "Ios17.add" : 130,
-      "Ios16.reduceMean" : 130,
-      "Ios17.batchNorm" : 65,
-      "Ios16.softmax" : 32,
-      "Ios16.gelu" : 34,
-      "Ios17.reshape" : 128
-    },
-    "computePrecision" : "Mixed (Float16, Float32, Int32)",
-    "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"
-    },
-    "userDefinedMetadata" : {
-      "com.github.apple.coremltools.source_dialect" : "TorchScript",
-      "com.github.apple.coremltools.source" : "torch==2.1.2",
-      "com.github.apple.coremltools.version" : "7.1"
-    },
-    "inputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 80 × 1 × 3000)",
-        "shortDescription" : "",
-        "shape" : "[1, 80, 1, 3000]",
-        "name" : "melspectrogram_features",
-        "type" : "MultiArray"
-      }
-    ],
-    "generatedClassName" : "AudioEncoder_mixedBitPalettized_5_7_bit",
-    "method" : "predict"
-  }
-]

openai_whisper-large-v2_1050MB/AudioEncoder.mlmodelc/weights/weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:02d17ca056a64aaa1a4588b45a230eabc7c1366dbd9f92e575479ead60f66135
-size 455247616

openai_whisper-large-v2_1050MB/MelSpectrogram.mlmodelc/analytics/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b065e1f3f876bc8dc2e67df6d54d8433a2352afca63e0aa986bb0080797a6164
-size 243

openai_whisper-large-v2_1050MB/MelSpectrogram.mlmodelc/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8449f42983b4f026e5e1c9fc369bbceaacf2159069e119fea43217dd3285a170
-size 328

openai_whisper-large-v2_1050MB/MelSpectrogram.mlmodelc/metadata.json

@@ -1,71 +0,0 @@
-[
-  {
-    "metadataOutputVersion" : "3.0",
-    "storagePrecision" : "Float16",
-    "outputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 80 × 1 × 3000)",
-        "shortDescription" : "",
-        "shape" : "[1, 80, 1, 3000]",
-        "name" : "melspectrogram_features",
-        "type" : "MultiArray"
-      }
-    ],
-    "modelParameters" : [
-
-    ],
-    "specificationVersion" : 8,
-    "mlProgramOperationTypeHistogram" : {
-      "Ios17.mul" : 2,
-      "Ios17.sub" : 1,
-      "Ios17.matmul" : 1,
-      "Ios17.conv" : 2,
-      "Ios17.log" : 1,
-      "Ios17.add" : 3,
-      "Ios16.square" : 2,
-      "Ios17.sliceByIndex" : 1,
-      "Ios17.expandDims" : 4,
-      "Ios17.maximum" : 1,
-      "Ios16.reduceMax" : 1,
-      "Ios17.squeeze" : 2,
-      "Ios17.reshape" : 2,
-      "Identity" : 1,
-      "Pad" : 1
-    },
-    "computePrecision" : "Mixed (Float16, Float32, Int32)",
-    "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"
-    },
-    "userDefinedMetadata" : {
-      "com.github.apple.coremltools.source_dialect" : "TorchScript",
-      "com.github.apple.coremltools.source" : "torch==2.1.2",
-      "com.github.apple.coremltools.version" : "7.1"
-    },
-    "inputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 480000)",
-        "shortDescription" : "",
-        "shape" : "[480000]",
-        "name" : "audio",
-        "type" : "MultiArray"
-      }
-    ],
-    "generatedClassName" : "MelSpectrogram",
-    "method" : "predict"
-  }
-]

openai_whisper-large-v2_1050MB/MelSpectrogram.mlmodelc/model.mil

@@ -1,66 +0,0 @@
-program(1.0)
-[buildInfo = dict<tensor<string, []>, tensor<string, []>>({{"coremlc-component-MIL", "5.33.5"}, {"coremlc-version", "1877.40.3"}, {"coremltools-component-torch", "2.1.2"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "7.1"}})]
-{
-    func main<ios17>(tensor<fp16, [480000]> audio) {
-            tensor<int32, [3]> var_10 = const()[name = tensor<string, []>("op_10"), val = tensor<int32, [3]>([1, 1, 480000])];
-            tensor<fp16, [1, 1, 480000]> var_11_cast_fp16 = reshape(shape = var_10, x = audio)[name = tensor<string, []>("op_11_cast_fp16")];
-            tensor<int32, [6]> input_1_pad_0 = const()[name = tensor<string, []>("input_1_pad_0"), val = tensor<int32, [6]>([0, 0, 0, 0, 200, 200])];
-            tensor<string, []> input_1_mode_0 = const()[name = tensor<string, []>("input_1_mode_0"), val = tensor<string, []>("reflect")];
-            tensor<fp16, []> input_1_constant_val_0_to_fp16 = const()[name = tensor<string, []>("input_1_constant_val_0_to_fp16"), val = tensor<fp16, []>(0x0p+0)];
-            tensor<fp16, [1, 1, 480400]> input_1_cast_fp16 = pad(constant_val = input_1_constant_val_0_to_fp16, mode = input_1_mode_0, pad = input_1_pad_0, x = var_11_cast_fp16)[name = tensor<string, []>("input_1_cast_fp16")];
-            tensor<int32, [1]> var_22 = const()[name = tensor<string, []>("op_22"), val = tensor<int32, [1]>([480400])];
-            tensor<fp16, [480400]> input_cast_fp16 = reshape(shape = var_22, x = input_1_cast_fp16)[name = tensor<string, []>("input_cast_fp16")];
-            tensor<int32, [1]> expand_dims_0_axes_0 = const()[name = tensor<string, []>("expand_dims_0_axes_0"), val = tensor<int32, [1]>([0])];
-            tensor<fp16, [1, 480400]> expand_dims_0_cast_fp16 = expand_dims(axes = expand_dims_0_axes_0, x = input_cast_fp16)[name = tensor<string, []>("expand_dims_0_cast_fp16")];
-            tensor<int32, [1]> expand_dims_3 = const()[name = tensor<string, []>("expand_dims_3"), val = tensor<int32, [1]>([160])];
-            tensor<int32, [1]> expand_dims_4_axes_0 = const()[name = tensor<string, []>("expand_dims_4_axes_0"), val = tensor<int32, [1]>([1])];
-            tensor<fp16, [1, 1, 480400]> expand_dims_4_cast_fp16 = expand_dims(axes = expand_dims_4_axes_0, x = expand_dims_0_cast_fp16)[name = tensor<string, []>("expand_dims_4_cast_fp16")];
-            tensor<string, []> conv_0_pad_type_0 = const()[name = tensor<string, []>("conv_0_pad_type_0"), val = tensor<string, []>("valid")];
-            tensor<int32, [2]> conv_0_pad_0 = const()[name = tensor<string, []>("conv_0_pad_0"), val = tensor<int32, [2]>([0, 0])];
-            tensor<int32, [1]> conv_0_dilations_0 = const()[name = tensor<string, []>("conv_0_dilations_0"), val = tensor<int32, [1]>([1])];
-            tensor<int32, []> conv_0_groups_0 = const()[name = tensor<string, []>("conv_0_groups_0"), val = tensor<int32, []>(1)];
-            tensor<fp16, [201, 1, 400]> expand_dims_1_to_fp16 = const()[name = tensor<string, []>("expand_dims_1_to_fp16"), val = tensor<fp16, [201, 1, 400]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(64)))];
-            tensor<fp16, [1, 201, 3001]> conv_0_cast_fp16 = conv(dilations = conv_0_dilations_0, groups = conv_0_groups_0, pad = conv_0_pad_0, pad_type = conv_0_pad_type_0, strides = expand_dims_3, weight = expand_dims_1_to_fp16, x = expand_dims_4_cast_fp16)[name = tensor<string, []>("conv_0_cast_fp16")];
-            tensor<string, []> conv_1_pad_type_0 = const()[name = tensor<string, []>("conv_1_pad_type_0"), val = tensor<string, []>("valid")];
-            tensor<int32, [2]> conv_1_pad_0 = const()[name = tensor<string, []>("conv_1_pad_0"), val = tensor<int32, [2]>([0, 0])];
-            tensor<int32, [1]> conv_1_dilations_0 = const()[name = tensor<string, []>("conv_1_dilations_0"), val = tensor<int32, [1]>([1])];
-            tensor<int32, []> conv_1_groups_0 = const()[name = tensor<string, []>("conv_1_groups_0"), val = tensor<int32, []>(1)];
-            tensor<fp16, [201, 1, 400]> expand_dims_2_to_fp16 = const()[name = tensor<string, []>("expand_dims_2_to_fp16"), val = tensor<fp16, [201, 1, 400]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(160960)))];
-            tensor<fp16, [1, 201, 3001]> conv_1_cast_fp16 = conv(dilations = conv_1_dilations_0, groups = conv_1_groups_0, pad = conv_1_pad_0, pad_type = conv_1_pad_type_0, strides = expand_dims_3, weight = expand_dims_2_to_fp16, x = expand_dims_4_cast_fp16)[name = tensor<string, []>("conv_1_cast_fp16")];
-            tensor<int32, [1]> squeeze_0_axes_0 = const()[name = tensor<string, []>("squeeze_0_axes_0"), val = tensor<int32, [1]>([0])];
-            tensor<fp16, [201, 3001]> squeeze_0_cast_fp16 = squeeze(axes = squeeze_0_axes_0, x = conv_0_cast_fp16)[name = tensor<string, []>("squeeze_0_cast_fp16")];
-            tensor<int32, [1]> squeeze_1_axes_0 = const()[name = tensor<string, []>("squeeze_1_axes_0"), val = tensor<int32, [1]>([0])];
-            tensor<fp16, [201, 3001]> squeeze_1_cast_fp16 = squeeze(axes = squeeze_1_axes_0, x = conv_1_cast_fp16)[name = tensor<string, []>("squeeze_1_cast_fp16")];
-            tensor<fp16, [201, 3001]> square_0_cast_fp16 = square(x = squeeze_0_cast_fp16)[name = tensor<string, []>("square_0_cast_fp16")];
-            tensor<fp16, [201, 3001]> square_1_cast_fp16 = square(x = squeeze_1_cast_fp16)[name = tensor<string, []>("square_1_cast_fp16")];
-            tensor<fp16, [201, 3001]> add_1_cast_fp16 = add(x = square_0_cast_fp16, y = square_1_cast_fp16)[name = tensor<string, []>("add_1_cast_fp16")];
-            tensor<fp16, [201, 3001]> magnitudes_1_cast_fp16 = identity(x = add_1_cast_fp16)[name = tensor<string, []>("magnitudes_1_cast_fp16")];
-            tensor<int32, [2]> magnitudes_begin_0 = const()[name = tensor<string, []>("magnitudes_begin_0"), val = tensor<int32, [2]>([0, 0])];
-            tensor<int32, [2]> magnitudes_end_0 = const()[name = tensor<string, []>("magnitudes_end_0"), val = tensor<int32, [2]>([201, 3000])];
-            tensor<bool, [2]> magnitudes_end_mask_0 = const()[name = tensor<string, []>("magnitudes_end_mask_0"), val = tensor<bool, [2]>([true, false])];
-            tensor<fp16, [201, 3000]> magnitudes_cast_fp16 = slice_by_index(begin = magnitudes_begin_0, end = magnitudes_end_0, end_mask = magnitudes_end_mask_0, x = magnitudes_1_cast_fp16)[name = tensor<string, []>("magnitudes_cast_fp16")];
-            tensor<bool, []> mel_spec_1_transpose_x_0 = const()[name = tensor<string, []>("mel_spec_1_transpose_x_0"), val = tensor<bool, []>(false)];
-            tensor<bool, []> mel_spec_1_transpose_y_0 = const()[name = tensor<string, []>("mel_spec_1_transpose_y_0"), val = tensor<bool, []>(false)];
-            tensor<fp16, [80, 201]> mel_filters_to_fp16 = const()[name = tensor<string, []>("mel_filters_to_fp16"), val = tensor<fp16, [80, 201]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(321856)))];
-            tensor<fp16, [80, 3000]> mel_spec_1_cast_fp16 = matmul(transpose_x = mel_spec_1_transpose_x_0, transpose_y = mel_spec_1_transpose_y_0, x = mel_filters_to_fp16, y = magnitudes_cast_fp16)[name = tensor<string, []>("mel_spec_1_cast_fp16")];
-            tensor<fp16, []> var_41_to_fp16 = const()[name = tensor<string, []>("op_41_to_fp16"), val = tensor<fp16, []>(0x1p-24)];
-            tensor<fp16, [80, 3000]> mel_spec_cast_fp16 = add(x = mel_spec_1_cast_fp16, y = var_41_to_fp16)[name = tensor<string, []>("mel_spec_cast_fp16")];
-            tensor<fp32, []> log_0_epsilon_0 = const()[name = tensor<string, []>("log_0_epsilon_0"), val = tensor<fp32, []>(0x1p-149)];
-            tensor<fp16, [80, 3000]> log_0_cast_fp16 = log(epsilon = log_0_epsilon_0, x = mel_spec_cast_fp16)[name = tensor<string, []>("log_0_cast_fp16")];
-            tensor<fp16, []> mul_0_y_0_to_fp16 = const()[name = tensor<string, []>("mul_0_y_0_to_fp16"), val = tensor<fp16, []>(0x1.bccp-2)];
-            tensor<fp16, [80, 3000]> mul_0_cast_fp16 = mul(x = log_0_cast_fp16, y = mul_0_y_0_to_fp16)[name = tensor<string, []>("mul_0_cast_fp16")];
-            tensor<bool, []> var_44_keep_dims_0 = const()[name = tensor<string, []>("op_44_keep_dims_0"), val = tensor<bool, []>(false)];
-            tensor<fp16, []> var_44_cast_fp16 = reduce_max(keep_dims = var_44_keep_dims_0, x = mul_0_cast_fp16)[name = tensor<string, []>("op_44_cast_fp16")];
-            tensor<fp16, []> var_46_to_fp16 = const()[name = tensor<string, []>("op_46_to_fp16"), val = tensor<fp16, []>(0x1p+3)];
-            tensor<fp16, []> var_47_cast_fp16 = sub(x = var_44_cast_fp16, y = var_46_to_fp16)[name = tensor<string, []>("op_47_cast_fp16")];
-            tensor<fp16, [80, 3000]> log_spec_3_cast_fp16 = maximum(x = mul_0_cast_fp16, y = var_47_cast_fp16)[name = tensor<string, []>("log_spec_3_cast_fp16")];
-            tensor<fp16, []> var_50_to_fp16 = const()[name = tensor<string, []>("op_50_to_fp16"), val = tensor<fp16, []>(0x1p+2)];
-            tensor<fp16, [80, 3000]> var_51_cast_fp16 = add(x = log_spec_3_cast_fp16, y = var_50_to_fp16)[name = tensor<string, []>("op_51_cast_fp16")];
-            tensor<fp16, []> _inversed_log_spec_y_0_to_fp16 = const()[name = tensor<string, []>("_inversed_log_spec_y_0_to_fp16"), val = tensor<fp16, []>(0x1p-2)];
-            tensor<fp16, [80, 3000]> _inversed_log_spec_cast_fp16 = mul(x = var_51_cast_fp16, y = _inversed_log_spec_y_0_to_fp16)[name = tensor<string, []>("_inversed_log_spec_cast_fp16")];
-            tensor<int32, [1]> var_55_axes_0 = const()[name = tensor<string, []>("op_55_axes_0"), val = tensor<int32, [1]>([0])];
-            tensor<fp16, [1, 80, 3000]> var_55_cast_fp16 = expand_dims(axes = var_55_axes_0, x = _inversed_log_spec_cast_fp16)[name = tensor<string, []>("op_55_cast_fp16")];
-            tensor<int32, [1]> var_62_axes_0 = const()[name = tensor<string, []>("op_62_axes_0"), val = tensor<int32, [1]>([2])];
-            tensor<fp16, [1, 80, 1, 3000]> melspectrogram_features = expand_dims(axes = var_62_axes_0, x = var_55_cast_fp16)[name = tensor<string, []>("op_62_cast_fp16")];
-        } -> (melspectrogram_features);
-}

openai_whisper-large-v2_1050MB/MelSpectrogram.mlmodelc/weights/weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:534ed6e716a28ef05a392cef2eabab4061ea709f8f0b9de25549976af04ee833
-size 354080

openai_whisper-large-v2_1050MB/TextDecoder.mlmodelc/analytics/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fa29f227123e4ef9158ceef783082d9d4b6d29983146fba4ea8374a5c3210ecc
-size 243

openai_whisper-large-v2_1050MB/TextDecoder.mlmodelc/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:62dea27334244885500adf21e60daafcc92270e904b33567118b299fb5725885
-size 597

openai_whisper-large-v2_1050MB/TextDecoder.mlmodelc/metadata.json

@@ -1,156 +0,0 @@
-[
-  {
-    "metadataOutputVersion" : "3.0",
-    "storagePrecision" : "Mixed (Float16, Palettized (4 bits), Palettized (6 bits))",
-    "outputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 1 × 51865)",
-        "shortDescription" : "",
-        "shape" : "[1, 1, 51865]",
-        "name" : "logits",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 40960 × 1 × 1)",
-        "shortDescription" : "",
-        "shape" : "[1, 40960, 1, 1]",
-        "name" : "key_cache_updates",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 40960 × 1 × 1)",
-        "shortDescription" : "",
-        "shape" : "[1, 40960, 1, 1]",
-        "name" : "value_cache_updates",
-        "type" : "MultiArray"
-      }
-    ],
-    "modelParameters" : [
-
-    ],
-    "specificationVersion" : 8,
-    "mlProgramOperationTypeHistogram" : {
-      "Ios17.reshape" : 256,
-      "Ios16.reduceMean" : 194,
-      "Ios16.softmax" : 64,
-      "Ios17.matmul" : 128,
-      "Ios17.transpose" : 1,
-      "Split" : 2,
-      "Ios17.expandDims" : 6,
-      "Ios17.add" : 610,
-      "Ios17.squeeze" : 1,
-      "Ios17.gather" : 2,
-      "Ios17.batchNorm" : 97,
-      "Ios16.gelu" : 32,
-      "Ios17.cast" : 1,
-      "Ios16.constexprLutToDense" : 320,
-      "Ios17.conv" : 960,
-      "Ios17.sub" : 98,
-      "Ios17.concat" : 2,
-      "Ios17.linear" : 1,
-      "Ios17.rsqrt" : 97,
-      "Ios17.mul" : 386
-    },
-    "computePrecision" : "Mixed (Float16, Float32, Int16, Int32)",
-    "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"
-    },
-    "userDefinedMetadata" : {
-      "com.github.apple.coremltools.source_dialect" : "TorchScript",
-      "com.github.apple.coremltools.source" : "torch==2.2.0",
-      "com.github.apple.coremltools.version" : "7.1"
-    },
-    "inputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Int32",
-        "formattedType" : "MultiArray (Int32 1)",
-        "shortDescription" : "",
-        "shape" : "[1]",
-        "name" : "input_ids",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Int32",
-        "formattedType" : "MultiArray (Int32 1)",
-        "shortDescription" : "",
-        "shape" : "[1]",
-        "name" : "cache_length",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 40960 × 1 × 448)",
-        "shortDescription" : "",
-        "shape" : "[1, 40960, 1, 448]",
-        "name" : "key_cache",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 40960 × 1 × 448)",
-        "shortDescription" : "",
-        "shape" : "[1, 40960, 1, 448]",
-        "name" : "value_cache",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 448)",
-        "shortDescription" : "",
-        "shape" : "[1, 448]",
-        "name" : "kv_cache_update_mask",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 1280 × 1 × 1500)",
-        "shortDescription" : "",
-        "shape" : "[1, 1280, 1, 1500]",
-        "name" : "encoder_output_embeds",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 448)",
-        "shortDescription" : "",
-        "shape" : "[1, 448]",
-        "name" : "decoder_key_padding_mask",
-        "type" : "MultiArray"
-      }
-    ],
-    "generatedClassName" : "TextDecoder_mixedBitPalettized_4_0_bit",
-    "method" : "predict"
-  }
-]

openai_whisper-large-v2_1050MB/TextDecoder.mlmodelc/weights/weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cb0e5002b78d10d7fb53bc434273202045ac9c7867a99b2cb3d282771ace6f9c
-size 592355826

openai_whisper-large-v2_1050MB/config.json

@@ -1 +0,0 @@
-{"_name_or_path": "openai/whisper-large-v2", "activation_dropout": 0.0, "activation_function": "gelu", "architectures": ["WhisperForConditionalGeneration"], "attention_dropout": 0.0, "begin_suppress_tokens": [220, 50257], "bos_token_id": 50257, "d_model": 1280, "decoder_attention_heads": 20, "decoder_ffn_dim": 5120, "decoder_layerdrop": 0.0, "decoder_layers": 32, "decoder_start_token_id": 50258, "dropout": 0.0, "encoder_attention_heads": 20, "encoder_ffn_dim": 5120, "encoder_layerdrop": 0.0, "encoder_layers": 32, "eos_token_id": 50257, "forced_decoder_ids": [[1, 50259], [2, 50359], [3, 50363]], "init_std": 0.02, "is_encoder_decoder": true, "max_length": 448, "max_source_positions": 1500, "max_target_positions": 448, "model_type": "whisper", "num_hidden_layers": 32, "num_mel_bins": 80, "pad_token_id": 50257, "scale_embedding": false, "suppress_tokens": [1, 2, 7, 8, 9, 10, 14, 25, 26, 27, 28, 29, 31, 58, 59, 60, 61, 62, 63, 90, 91, 92, 93, 359, 503, 522, 542, 873, 893, 902, 918, 922, 931, 1350, 1853, 1982, 2460, 2627, 3246, 3253, 3268, 3536, 3846, 3961, 4183, 4667, 6585, 6647, 7273, 9061, 9383, 10428, 10929, 11938, 12033, 12331, 12562, 13793, 14157, 14635, 15265, 15618, 16553, 16604, 18362, 18956, 20075, 21675, 22520, 26130, 26161, 26435, 28279, 29464, 31650, 32302, 32470, 36865, 42863, 47425, 49870, 50254, 50258, 50358, 50359, 50360, 50361, 50362], "torch_dtype": "float32", "transformers_version": "4.27.0.dev0", "use_cache": true, "vocab_size": 51865}

openai_whisper-large-v2_1050MB/generation_config.json

@@ -1 +0,0 @@
-{"alignment_heads": [[10, 12], [13, 17], [16, 11], [16, 12], [16, 13], [17, 15], [17, 16], [18, 4], [18, 11], [18, 19], [19, 11], [21, 2], [21, 3], [22, 3], [22, 9], [22, 12], [23, 5], [23, 7], [23, 13], [25, 5], [26, 1], [26, 12], [27, 15]], "begin_suppress_tokens": [220, 50257], "bos_token_id": 50257, "decoder_start_token_id": 50258, "eos_token_id": 50257, "forced_decoder_ids": [[1, null], [2, 50359]], "is_multilingual": true, "lang_to_id": {"<|af|>": 50327, "<|am|>": 50334, "<|ar|>": 50272, "<|as|>": 50350, "<|az|>": 50304, "<|ba|>": 50355, "<|be|>": 50330, "<|bg|>": 50292, "<|bn|>": 50302, "<|bo|>": 50347, "<|br|>": 50309, "<|bs|>": 50315, "<|ca|>": 50270, "<|cs|>": 50283, "<|cy|>": 50297, "<|da|>": 50285, "<|de|>": 50261, "<|el|>": 50281, "<|en|>": 50259, "<|es|>": 50262, "<|et|>": 50307, "<|eu|>": 50310, "<|fa|>": 50300, "<|fi|>": 50277, "<|fo|>": 50338, "<|fr|>": 50265, "<|gl|>": 50319, "<|gu|>": 50333, "<|haw|>": 50352, "<|ha|>": 50354, "<|he|>": 50279, "<|hi|>": 50276, "<|hr|>": 50291, "<|ht|>": 50339, "<|hu|>": 50286, "<|hy|>": 50312, "<|id|>": 50275, "<|is|>": 50311, "<|it|>": 50274, "<|ja|>": 50266, "<|jw|>": 50356, "<|ka|>": 50329, "<|kk|>": 50316, "<|km|>": 50323, "<|kn|>": 50306, "<|ko|>": 50264, "<|la|>": 50294, "<|lb|>": 50345, "<|ln|>": 50353, "<|lo|>": 50336, "<|lt|>": 50293, "<|lv|>": 50301, "<|mg|>": 50349, "<|mi|>": 50295, "<|mk|>": 50308, "<|ml|>": 50296, "<|mn|>": 50314, "<|mr|>": 50320, "<|ms|>": 50282, "<|mt|>": 50343, "<|my|>": 50346, "<|ne|>": 50313, "<|nl|>": 50271, "<|nn|>": 50342, "<|no|>": 50288, "<|oc|>": 50328, "<|pa|>": 50321, "<|pl|>": 50269, "<|ps|>": 50340, "<|pt|>": 50267, "<|ro|>": 50284, "<|ru|>": 50263, "<|sa|>": 50344, "<|sd|>": 50332, "<|si|>": 50322, "<|sk|>": 50298, "<|sl|>": 50305, "<|sn|>": 50324, "<|so|>": 50326, "<|sq|>": 50317, "<|sr|>": 50303, "<|su|>": 50357, "<|sv|>": 50273, "<|sw|>": 50318, "<|ta|>": 50287, "<|te|>": 50299, "<|tg|>": 50331, "<|th|>": 50289, "<|tk|>": 50341, "<|tl|>": 50348, "<|tr|>": 50268, "<|tt|>": 50351, "<|uk|>": 50280, "<|ur|>": 50290, "<|uz|>": 50337, "<|vi|>": 50278, "<|yi|>": 50335, "<|yo|>": 50325, "<|zh|>": 50260}, "max_initial_timestamp_index": 50, "max_length": 448, "no_timestamps_token_id": 50363, "pad_token_id": 50257, "prev_sot_token_id": 50361, "return_timestamps": false, "suppress_tokens": [1, 2, 7, 8, 9, 10, 14, 25, 26, 27, 28, 29, 31, 58, 59, 60, 61, 62, 63, 90, 91, 92, 93, 359, 503, 522, 542, 873, 893, 902, 918, 922, 931, 1350, 1853, 1982, 2460, 2627, 3246, 3253, 3268, 3536, 3846, 3961, 4183, 4667, 6585, 6647, 7273, 9061, 9383, 10428, 10929, 11938, 12033, 12331, 12562, 13793, 14157, 14635, 15265, 15618, 16553, 16604, 18362, 18956, 20075, 21675, 22520, 26130, 26161, 26435, 28279, 29464, 31650, 32302, 32470, 36865, 42863, 47425, 49870, 50254, 50258, 50358, 50359, 50360, 50361, 50362], "task_to_id": {"transcribe": 50359, "translate": 50358}, "transformers_version": "4.31.0.dev0"}

openai_whisper-large-v2_turbo_1022MB/AudioEncoder.mlmodelc/analytics/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:246bfd29afc3ea7c5e225152469442ffe4064236c3cd9b9c66872c7cf4ac2c72
-size 243

openai_whisper-large-v2_turbo_1022MB/AudioEncoder.mlmodelc/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e30541466a5715be01aa4874597a0c84b827f1d5377cbe89e379bd6f369e851e
-size 347

openai_whisper-large-v2_turbo_1022MB/AudioEncoder.mlmodelc/metadata.json

@@ -1,70 +0,0 @@
-[
-  {
-    "metadataOutputVersion" : "3.0",
-    "storagePrecision" : "Mixed (Float16, Palettized (4 bits))",
-    "outputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 1280 × 1 × 1500)",
-        "shortDescription" : "",
-        "shape" : "[1, 1280, 1, 1500]",
-        "name" : "encoder_output_embeds",
-        "type" : "MultiArray"
-      }
-    ],
-    "modelParameters" : [
-
-    ],
-    "specificationVersion" : 8,
-    "mlProgramOperationTypeHistogram" : {
-      "Ios17.mul" : 2690,
-      "Ios17.transpose" : 32,
-      "Ios17.rsqrt" : 65,
-      "Ios16.constexprLutToDense" : 182,
-      "Ios17.conv" : 194,
-      "Ios17.sub" : 65,
-      "Ios16.einsum" : 5120,
-      "Ios17.concat" : 672,
-      "Ios17.add" : 130,
-      "Ios16.reduceMean" : 130,
-      "Ios17.batchNorm" : 65,
-      "Ios17.sliceByIndex" : 4480,
-      "Ios16.softmax" : 2560,
-      "Ios16.gelu" : 34
-    },
-    "computePrecision" : "Mixed (Float16, Float32, Int32)",
-    "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"
-    },
-    "userDefinedMetadata" : {
-      "com.github.apple.coremltools.source_dialect" : "TorchScript",
-      "com.github.apple.coremltools.source" : "torch==2.1.2",
-      "com.github.apple.coremltools.version" : "7.1"
-    },
-    "inputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 80 × 1 × 3000)",
-        "shortDescription" : "",
-        "shape" : "[1, 80, 1, 3000]",
-        "name" : "melspectrogram_features",
-        "type" : "MultiArray"
-      }
-    ],
-    "generatedClassName" : "AudioEncoder_mixedBitPalettized_5_3_bit",
-    "method" : "predict"
-  }
-]

openai_whisper-large-v2_turbo_1022MB/AudioEncoder.mlmodelc/weights/weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5998c3da8d47af4ce963c3905a072ee4eebf181610ea3a1a27cd682f138d052b
-size 420841856

openai_whisper-large-v2_turbo_1022MB/MelSpectrogram.mlmodelc/analytics/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b065e1f3f876bc8dc2e67df6d54d8433a2352afca63e0aa986bb0080797a6164
-size 243

openai_whisper-large-v2_turbo_1022MB/MelSpectrogram.mlmodelc/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:95769e69794de49c2f2d0fa44b99605449f7259ff804161a0e01afc74a9fa5ef
-size 328

openai_whisper-large-v2_turbo_1022MB/MelSpectrogram.mlmodelc/metadata.json

@@ -1,71 +0,0 @@
-[
-  {
-    "metadataOutputVersion" : "3.0",
-    "storagePrecision" : "Float16",
-    "outputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 80 × 1 × 3000)",
-        "shortDescription" : "",
-        "shape" : "[1, 80, 1, 3000]",
-        "name" : "melspectrogram_features",
-        "type" : "MultiArray"
-      }
-    ],
-    "modelParameters" : [
-
-    ],
-    "specificationVersion" : 8,
-    "mlProgramOperationTypeHistogram" : {
-      "Ios17.mul" : 2,
-      "Ios17.sub" : 1,
-      "Ios17.matmul" : 1,
-      "Ios17.conv" : 2,
-      "Ios17.log" : 1,
-      "Ios17.add" : 3,
-      "Ios16.square" : 2,
-      "Ios17.sliceByIndex" : 1,
-      "Ios17.expandDims" : 4,
-      "Ios17.maximum" : 1,
-      "Ios16.reduceMax" : 1,
-      "Ios17.squeeze" : 2,
-      "Ios17.reshape" : 2,
-      "Identity" : 1,
-      "Pad" : 1
-    },
-    "computePrecision" : "Mixed (Float16, Float32, Int32)",
-    "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"
-    },
-    "userDefinedMetadata" : {
-      "com.github.apple.coremltools.source_dialect" : "TorchScript",
-      "com.github.apple.coremltools.source" : "torch==2.1.2",
-      "com.github.apple.coremltools.version" : "7.1"
-    },
-    "inputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 480000)",
-        "shortDescription" : "",
-        "shape" : "[480000]",
-        "name" : "audio",
-        "type" : "MultiArray"
-      }
-    ],
-    "generatedClassName" : "MelSpectrogram",
-    "method" : "predict"
-  }
-]

openai_whisper-large-v2_turbo_1022MB/MelSpectrogram.mlmodelc/model.mil

@@ -1,66 +0,0 @@
-program(1.0)
-[buildInfo = dict<tensor<string, []>, tensor<string, []>>({{"coremlc-component-MIL", "5.33.5"}, {"coremlc-version", "1877.40.3"}, {"coremltools-component-torch", "2.1.2"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "7.1"}})]
-{
-    func main<ios17>(tensor<fp16, [480000]> audio) {
-            tensor<int32, [3]> var_10 = const()[name = tensor<string, []>("op_10"), val = tensor<int32, [3]>([1, 1, 480000])];
-            tensor<fp16, [1, 1, 480000]> var_11_cast_fp16 = reshape(shape = var_10, x = audio)[name = tensor<string, []>("op_11_cast_fp16")];
-            tensor<int32, [6]> input_1_pad_0 = const()[name = tensor<string, []>("input_1_pad_0"), val = tensor<int32, [6]>([0, 0, 0, 0, 200, 200])];
-            tensor<string, []> input_1_mode_0 = const()[name = tensor<string, []>("input_1_mode_0"), val = tensor<string, []>("reflect")];
-            tensor<fp16, []> input_1_constant_val_0_to_fp16 = const()[name = tensor<string, []>("input_1_constant_val_0_to_fp16"), val = tensor<fp16, []>(0x0p+0)];
-            tensor<fp16, [1, 1, 480400]> input_1_cast_fp16 = pad(constant_val = input_1_constant_val_0_to_fp16, mode = input_1_mode_0, pad = input_1_pad_0, x = var_11_cast_fp16)[name = tensor<string, []>("input_1_cast_fp16")];
-            tensor<int32, [1]> var_22 = const()[name = tensor<string, []>("op_22"), val = tensor<int32, [1]>([480400])];
-            tensor<fp16, [480400]> input_cast_fp16 = reshape(shape = var_22, x = input_1_cast_fp16)[name = tensor<string, []>("input_cast_fp16")];
-            tensor<int32, [1]> expand_dims_0_axes_0 = const()[name = tensor<string, []>("expand_dims_0_axes_0"), val = tensor<int32, [1]>([0])];
-            tensor<fp16, [1, 480400]> expand_dims_0_cast_fp16 = expand_dims(axes = expand_dims_0_axes_0, x = input_cast_fp16)[name = tensor<string, []>("expand_dims_0_cast_fp16")];
-            tensor<int32, [1]> expand_dims_3 = const()[name = tensor<string, []>("expand_dims_3"), val = tensor<int32, [1]>([160])];
-            tensor<int32, [1]> expand_dims_4_axes_0 = const()[name = tensor<string, []>("expand_dims_4_axes_0"), val = tensor<int32, [1]>([1])];
-            tensor<fp16, [1, 1, 480400]> expand_dims_4_cast_fp16 = expand_dims(axes = expand_dims_4_axes_0, x = expand_dims_0_cast_fp16)[name = tensor<string, []>("expand_dims_4_cast_fp16")];
-            tensor<string, []> conv_0_pad_type_0 = const()[name = tensor<string, []>("conv_0_pad_type_0"), val = tensor<string, []>("valid")];
-            tensor<int32, [2]> conv_0_pad_0 = const()[name = tensor<string, []>("conv_0_pad_0"), val = tensor<int32, [2]>([0, 0])];
-            tensor<int32, [1]> conv_0_dilations_0 = const()[name = tensor<string, []>("conv_0_dilations_0"), val = tensor<int32, [1]>([1])];
-            tensor<int32, []> conv_0_groups_0 = const()[name = tensor<string, []>("conv_0_groups_0"), val = tensor<int32, []>(1)];
-            tensor<fp16, [201, 1, 400]> expand_dims_1_to_fp16 = const()[name = tensor<string, []>("expand_dims_1_to_fp16"), val = tensor<fp16, [201, 1, 400]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(64)))];
-            tensor<fp16, [1, 201, 3001]> conv_0_cast_fp16 = conv(dilations = conv_0_dilations_0, groups = conv_0_groups_0, pad = conv_0_pad_0, pad_type = conv_0_pad_type_0, strides = expand_dims_3, weight = expand_dims_1_to_fp16, x = expand_dims_4_cast_fp16)[name = tensor<string, []>("conv_0_cast_fp16")];
-            tensor<string, []> conv_1_pad_type_0 = const()[name = tensor<string, []>("conv_1_pad_type_0"), val = tensor<string, []>("valid")];
-            tensor<int32, [2]> conv_1_pad_0 = const()[name = tensor<string, []>("conv_1_pad_0"), val = tensor<int32, [2]>([0, 0])];
-            tensor<int32, [1]> conv_1_dilations_0 = const()[name = tensor<string, []>("conv_1_dilations_0"), val = tensor<int32, [1]>([1])];
-            tensor<int32, []> conv_1_groups_0 = const()[name = tensor<string, []>("conv_1_groups_0"), val = tensor<int32, []>(1)];
-            tensor<fp16, [201, 1, 400]> expand_dims_2_to_fp16 = const()[name = tensor<string, []>("expand_dims_2_to_fp16"), val = tensor<fp16, [201, 1, 400]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(160960)))];
-            tensor<fp16, [1, 201, 3001]> conv_1_cast_fp16 = conv(dilations = conv_1_dilations_0, groups = conv_1_groups_0, pad = conv_1_pad_0, pad_type = conv_1_pad_type_0, strides = expand_dims_3, weight = expand_dims_2_to_fp16, x = expand_dims_4_cast_fp16)[name = tensor<string, []>("conv_1_cast_fp16")];
-            tensor<int32, [1]> squeeze_0_axes_0 = const()[name = tensor<string, []>("squeeze_0_axes_0"), val = tensor<int32, [1]>([0])];
-            tensor<fp16, [201, 3001]> squeeze_0_cast_fp16 = squeeze(axes = squeeze_0_axes_0, x = conv_0_cast_fp16)[name = tensor<string, []>("squeeze_0_cast_fp16")];
-            tensor<int32, [1]> squeeze_1_axes_0 = const()[name = tensor<string, []>("squeeze_1_axes_0"), val = tensor<int32, [1]>([0])];
-            tensor<fp16, [201, 3001]> squeeze_1_cast_fp16 = squeeze(axes = squeeze_1_axes_0, x = conv_1_cast_fp16)[name = tensor<string, []>("squeeze_1_cast_fp16")];
-            tensor<fp16, [201, 3001]> square_0_cast_fp16 = square(x = squeeze_0_cast_fp16)[name = tensor<string, []>("square_0_cast_fp16")];
-            tensor<fp16, [201, 3001]> square_1_cast_fp16 = square(x = squeeze_1_cast_fp16)[name = tensor<string, []>("square_1_cast_fp16")];
-            tensor<fp16, [201, 3001]> add_1_cast_fp16 = add(x = square_0_cast_fp16, y = square_1_cast_fp16)[name = tensor<string, []>("add_1_cast_fp16")];
-            tensor<fp16, [201, 3001]> magnitudes_1_cast_fp16 = identity(x = add_1_cast_fp16)[name = tensor<string, []>("magnitudes_1_cast_fp16")];
-            tensor<int32, [2]> magnitudes_begin_0 = const()[name = tensor<string, []>("magnitudes_begin_0"), val = tensor<int32, [2]>([0, 0])];
-            tensor<int32, [2]> magnitudes_end_0 = const()[name = tensor<string, []>("magnitudes_end_0"), val = tensor<int32, [2]>([201, 3000])];
-            tensor<bool, [2]> magnitudes_end_mask_0 = const()[name = tensor<string, []>("magnitudes_end_mask_0"), val = tensor<bool, [2]>([true, false])];
-            tensor<fp16, [201, 3000]> magnitudes_cast_fp16 = slice_by_index(begin = magnitudes_begin_0, end = magnitudes_end_0, end_mask = magnitudes_end_mask_0, x = magnitudes_1_cast_fp16)[name = tensor<string, []>("magnitudes_cast_fp16")];
-            tensor<bool, []> mel_spec_1_transpose_x_0 = const()[name = tensor<string, []>("mel_spec_1_transpose_x_0"), val = tensor<bool, []>(false)];
-            tensor<bool, []> mel_spec_1_transpose_y_0 = const()[name = tensor<string, []>("mel_spec_1_transpose_y_0"), val = tensor<bool, []>(false)];
-            tensor<fp16, [80, 201]> mel_filters_to_fp16 = const()[name = tensor<string, []>("mel_filters_to_fp16"), val = tensor<fp16, [80, 201]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(321856)))];
-            tensor<fp16, [80, 3000]> mel_spec_1_cast_fp16 = matmul(transpose_x = mel_spec_1_transpose_x_0, transpose_y = mel_spec_1_transpose_y_0, x = mel_filters_to_fp16, y = magnitudes_cast_fp16)[name = tensor<string, []>("mel_spec_1_cast_fp16")];
-            tensor<fp16, []> var_41_to_fp16 = const()[name = tensor<string, []>("op_41_to_fp16"), val = tensor<fp16, []>(0x1p-24)];
-            tensor<fp16, [80, 3000]> mel_spec_cast_fp16 = add(x = mel_spec_1_cast_fp16, y = var_41_to_fp16)[name = tensor<string, []>("mel_spec_cast_fp16")];
-            tensor<fp32, []> log_0_epsilon_0 = const()[name = tensor<string, []>("log_0_epsilon_0"), val = tensor<fp32, []>(0x1p-149)];
-            tensor<fp16, [80, 3000]> log_0_cast_fp16 = log(epsilon = log_0_epsilon_0, x = mel_spec_cast_fp16)[name = tensor<string, []>("log_0_cast_fp16")];
-            tensor<fp16, []> mul_0_y_0_to_fp16 = const()[name = tensor<string, []>("mul_0_y_0_to_fp16"), val = tensor<fp16, []>(0x1.bccp-2)];
-            tensor<fp16, [80, 3000]> mul_0_cast_fp16 = mul(x = log_0_cast_fp16, y = mul_0_y_0_to_fp16)[name = tensor<string, []>("mul_0_cast_fp16")];
-            tensor<bool, []> var_44_keep_dims_0 = const()[name = tensor<string, []>("op_44_keep_dims_0"), val = tensor<bool, []>(false)];
-            tensor<fp16, []> var_44_cast_fp16 = reduce_max(keep_dims = var_44_keep_dims_0, x = mul_0_cast_fp16)[name = tensor<string, []>("op_44_cast_fp16")];
-            tensor<fp16, []> var_46_to_fp16 = const()[name = tensor<string, []>("op_46_to_fp16"), val = tensor<fp16, []>(0x1p+3)];
-            tensor<fp16, []> var_47_cast_fp16 = sub(x = var_44_cast_fp16, y = var_46_to_fp16)[name = tensor<string, []>("op_47_cast_fp16")];
-            tensor<fp16, [80, 3000]> log_spec_3_cast_fp16 = maximum(x = mul_0_cast_fp16, y = var_47_cast_fp16)[name = tensor<string, []>("log_spec_3_cast_fp16")];
-            tensor<fp16, []> var_50_to_fp16 = const()[name = tensor<string, []>("op_50_to_fp16"), val = tensor<fp16, []>(0x1p+2)];
-            tensor<fp16, [80, 3000]> var_51_cast_fp16 = add(x = log_spec_3_cast_fp16, y = var_50_to_fp16)[name = tensor<string, []>("op_51_cast_fp16")];
-            tensor<fp16, []> _inversed_log_spec_y_0_to_fp16 = const()[name = tensor<string, []>("_inversed_log_spec_y_0_to_fp16"), val = tensor<fp16, []>(0x1p-2)];
-            tensor<fp16, [80, 3000]> _inversed_log_spec_cast_fp16 = mul(x = var_51_cast_fp16, y = _inversed_log_spec_y_0_to_fp16)[name = tensor<string, []>("_inversed_log_spec_cast_fp16")];
-            tensor<int32, [1]> var_55_axes_0 = const()[name = tensor<string, []>("op_55_axes_0"), val = tensor<int32, [1]>([0])];
-            tensor<fp16, [1, 80, 3000]> var_55_cast_fp16 = expand_dims(axes = var_55_axes_0, x = _inversed_log_spec_cast_fp16)[name = tensor<string, []>("op_55_cast_fp16")];
-            tensor<int32, [1]> var_62_axes_0 = const()[name = tensor<string, []>("op_62_axes_0"), val = tensor<int32, [1]>([2])];
-            tensor<fp16, [1, 80, 1, 3000]> melspectrogram_features = expand_dims(axes = var_62_axes_0, x = var_55_cast_fp16)[name = tensor<string, []>("op_62_cast_fp16")];
-        } -> (melspectrogram_features);
-}

openai_whisper-large-v2_turbo_1022MB/MelSpectrogram.mlmodelc/weights/weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:707270213d25adca3dbe86f655d1869d9ef238a8701c518051a9fc362f2767cf
-size 354080

openai_whisper-large-v2_turbo_1022MB/TextDecoder.mlmodelc/analytics/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:478485e8d725af9db4d58a76f84d40eeeea63e117ec0964c61d0acbe4d05653b
-size 243

openai_whisper-large-v2_turbo_1022MB/TextDecoder.mlmodelc/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f02c018ec9827748ba0db08bc8e94faf6c6dfc609a091728171634cd938f4616
-size 597

openai_whisper-large-v2_turbo_1022MB/TextDecoder.mlmodelc/metadata.json

@@ -1,156 +0,0 @@
-[
-  {
-    "metadataOutputVersion" : "3.0",
-    "storagePrecision" : "Mixed (Float16, Palettized (4 bits), Palettized (6 bits))",
-    "outputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 1 × 51865)",
-        "shortDescription" : "",
-        "shape" : "[1, 1, 51865]",
-        "name" : "logits",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 40960 × 1 × 1)",
-        "shortDescription" : "",
-        "shape" : "[1, 40960, 1, 1]",
-        "name" : "key_cache_updates",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 40960 × 1 × 1)",
-        "shortDescription" : "",
-        "shape" : "[1, 40960, 1, 1]",
-        "name" : "value_cache_updates",
-        "type" : "MultiArray"
-      }
-    ],
-    "modelParameters" : [
-
-    ],
-    "specificationVersion" : 8,
-    "mlProgramOperationTypeHistogram" : {
-      "Ios17.reshape" : 256,
-      "Ios16.reduceMean" : 194,
-      "Ios16.softmax" : 64,
-      "Ios17.matmul" : 128,
-      "Ios17.transpose" : 1,
-      "Split" : 2,
-      "Ios17.expandDims" : 6,
-      "Ios17.add" : 610,
-      "Ios17.squeeze" : 1,
-      "Ios17.gather" : 2,
-      "Ios17.batchNorm" : 97,
-      "Ios16.gelu" : 32,
-      "Ios17.cast" : 1,
-      "Ios16.constexprLutToDense" : 320,
-      "Ios17.conv" : 960,
-      "Ios17.sub" : 98,
-      "Ios17.concat" : 2,
-      "Ios17.linear" : 1,
-      "Ios17.rsqrt" : 97,
-      "Ios17.mul" : 386
-    },
-    "computePrecision" : "Mixed (Float16, Float32, Int16, Int32)",
-    "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"
-    },
-    "userDefinedMetadata" : {
-      "com.github.apple.coremltools.source_dialect" : "TorchScript",
-      "com.github.apple.coremltools.version" : "7.1",
-      "com.github.apple.coremltools.source" : "torch==2.2.0"
-    },
-    "inputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Int32",
-        "formattedType" : "MultiArray (Int32 1)",
-        "shortDescription" : "",
-        "shape" : "[1]",
-        "name" : "input_ids",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Int32",
-        "formattedType" : "MultiArray (Int32 1)",
-        "shortDescription" : "",
-        "shape" : "[1]",
-        "name" : "cache_length",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 40960 × 1 × 224)",
-        "shortDescription" : "",
-        "shape" : "[1, 40960, 1, 224]",
-        "name" : "key_cache",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 40960 × 1 × 224)",
-        "shortDescription" : "",
-        "shape" : "[1, 40960, 1, 224]",
-        "name" : "value_cache",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 224)",
-        "shortDescription" : "",
-        "shape" : "[1, 224]",
-        "name" : "kv_cache_update_mask",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 1280 × 1 × 1500)",
-        "shortDescription" : "",
-        "shape" : "[1, 1280, 1, 1500]",
-        "name" : "encoder_output_embeds",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 224)",
-        "shortDescription" : "",
-        "shape" : "[1, 224]",
-        "name" : "decoder_key_padding_mask",
-        "type" : "MultiArray"
-      }
-    ],
-    "generatedClassName" : "TextDecoder_mixedBitPalettized_4_0_bit",
-    "method" : "predict"
-  }
-]

openai_whisper-large-v2_turbo_1022MB/TextDecoder.mlmodelc/weights/weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fc7ce43303c28cac9849fce0fbda83b9eeef9974b818eb950de98dcfee4f53c3
-size 592355826

openai_whisper-large-v2_turbo_1022MB/TextDecoderContextPrefill.mlmodelc/analytics/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6b87105685997a16df6e8b898c60bae02570b0933e4647c7a224391049350501
-size 243

openai_whisper-large-v2_turbo_1022MB/TextDecoderContextPrefill.mlmodelc/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1eecac96214b81d27dadbf5ff5922428ec0c2319bf2ddb2c3fc2289af4e78a72
-size 382

openai_whisper-large-v2_turbo_1022MB/TextDecoderContextPrefill.mlmodelc/metadata.json

@@ -1,82 +0,0 @@
-[
-  {
-    "metadataOutputVersion" : "3.0",
-    "storagePrecision" : "Float16",
-    "outputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 40960 × 1 × 3)",
-        "shortDescription" : "",
-        "shape" : "[1, 40960, 1, 3]",
-        "name" : "key_cache_prefill",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 40960 × 1 × 3)",
-        "shortDescription" : "",
-        "shape" : "[1, 40960, 1, 3]",
-        "name" : "value_cache_prefill",
-        "type" : "MultiArray"
-      }
-    ],
-    "modelParameters" : [
-
-    ],
-    "specificationVersion" : 8,
-    "mlProgramOperationTypeHistogram" : {
-      "Ios17.mul" : 1,
-      "Ios17.cast" : 1,
-      "Ios17.sub" : 1,
-      "Ios17.reshape" : 2,
-      "Ios17.add" : 1,
-      "Ios17.gather" : 2
-    },
-    "computePrecision" : "Mixed (Float16, Int16, Int32)",
-    "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"
-    },
-    "userDefinedMetadata" : {
-      "com.github.apple.coremltools.source_dialect" : "TorchScript",
-      "com.github.apple.coremltools.source" : "torch==2.2.0",
-      "com.github.apple.coremltools.version" : "7.1"
-    },
-    "inputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Int32",
-        "formattedType" : "MultiArray (Int32 1)",
-        "shortDescription" : "",
-        "shape" : "[1]",
-        "name" : "task",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Int32",
-        "formattedType" : "MultiArray (Int32 1)",
-        "shortDescription" : "",
-        "shape" : "[1]",
-        "name" : "language",
-        "type" : "MultiArray"
-      }
-    ],
-    "generatedClassName" : "TextDecoderContextPrefill",
-    "method" : "predict"
-  }
-]

openai_whisper-large-v2_turbo_1022MB/TextDecoderContextPrefill.mlmodelc/model.mil

@@ -1,27 +0,0 @@
-program(1.0)
-[buildInfo = dict<tensor<string, []>, tensor<string, []>>({{"coremlc-component-MIL", "5.33.5"}, {"coremlc-version", "1877.40.3"}, {"coremltools-component-torch", "2.2.0"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "7.1"}})]
-{
-    func main<ios17>(tensor<int32, [1]> language, tensor<int32, [1]> task) {
-            tensor<int32, []> var_6 = const()[name = tensor<string, []>("op_6"), val = tensor<int32, []>(50259)];
-            tensor<int32, [1]> var_7 = sub(x = language, y = var_6)[name = tensor<string, []>("op_7")];
-            tensor<int32, []> var_8 = const()[name = tensor<string, []>("op_8"), val = tensor<int32, []>(2)];
-            tensor<int32, [1]> var_9 = mul(x = var_7, y = var_8)[name = tensor<string, []>("op_9")];
-            tensor<int32, [1]> input = add(x = var_9, y = task)[name = tensor<string, []>("input")];
-            tensor<int32, []> var_15_axis_0 = const()[name = tensor<string, []>("op_15_axis_0"), val = tensor<int32, []>(0)];
-            tensor<int32, []> var_15_batch_dims_0 = const()[name = tensor<string, []>("op_15_batch_dims_0"), val = tensor<int32, []>(0)];
-            tensor<bool, []> var_15_validate_indices_0 = const()[name = tensor<string, []>("op_15_validate_indices_0"), val = tensor<bool, []>(false)];
-            tensor<fp16, [198, 122880]> key_cache_lut_weight_to_fp16 = const()[name = tensor<string, []>("key_cache_lut_weight_to_fp16"), val = tensor<fp16, [198, 122880]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(64)))];
-            tensor<string, []> input_to_int16_dtype_0 = const()[name = tensor<string, []>("input_to_int16_dtype_0"), val = tensor<string, []>("int16")];
-            tensor<int16, [1]> cast_6 = cast(dtype = input_to_int16_dtype_0, x = input)[name = tensor<string, []>("cast_6")];
-            tensor<fp16, [1, 122880]> var_15_cast_fp16_cast_int16 = gather(axis = var_15_axis_0, batch_dims = var_15_batch_dims_0, indices = cast_6, validate_indices = var_15_validate_indices_0, x = key_cache_lut_weight_to_fp16)[name = tensor<string, []>("op_15_cast_fp16_cast_int16")];
-            tensor<int32, [4]> var_20 = const()[name = tensor<string, []>("op_20"), val = tensor<int32, [4]>([1, 40960, 1, 3])];
-            tensor<fp16, [1, 40960, 1, 3]> key_cache_prefill = reshape(shape = var_20, x = var_15_cast_fp16_cast_int16)[name = tensor<string, []>("op_21_cast_fp16")];
-            tensor<int32, []> var_25_axis_0 = const()[name = tensor<string, []>("op_25_axis_0"), val = tensor<int32, []>(0)];
-            tensor<int32, []> var_25_batch_dims_0 = const()[name = tensor<string, []>("op_25_batch_dims_0"), val = tensor<int32, []>(0)];
-            tensor<bool, []> var_25_validate_indices_0 = const()[name = tensor<string, []>("op_25_validate_indices_0"), val = tensor<bool, []>(false)];
-            tensor<fp16, [198, 122880]> value_cache_lut_weight_to_fp16 = const()[name = tensor<string, []>("value_cache_lut_weight_to_fp16"), val = tensor<fp16, [198, 122880]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(48660608)))];
-            tensor<fp16, [1, 122880]> var_25_cast_fp16_cast_int16 = gather(axis = var_25_axis_0, batch_dims = var_25_batch_dims_0, indices = cast_6, validate_indices = var_25_validate_indices_0, x = value_cache_lut_weight_to_fp16)[name = tensor<string, []>("op_25_cast_fp16_cast_int16")];
-            tensor<int32, [4]> var_30 = const()[name = tensor<string, []>("op_30"), val = tensor<int32, [4]>([1, 40960, 1, 3])];
-            tensor<fp16, [1, 40960, 1, 3]> value_cache_prefill = reshape(shape = var_30, x = var_25_cast_fp16_cast_int16)[name = tensor<string, []>("op_31_cast_fp16")];
-        } -> (key_cache_prefill, value_cache_prefill);
-}

openai_whisper-large-v2_turbo_1022MB/TextDecoderContextPrefill.mlmodelc/weights/weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dc33403e412cb5cc604df990ce377f507211126aa07635686095bc043910f9b3
-size 97321152

openai_whisper-large-v2_turbo_1022MB/config.json

@@ -1 +0,0 @@
-{"_name_or_path": "openai/whisper-large-v2", "activation_dropout": 0.0, "activation_function": "gelu", "architectures": ["WhisperForConditionalGeneration"], "attention_dropout": 0.0, "begin_suppress_tokens": [220, 50257], "bos_token_id": 50257, "d_model": 1280, "decoder_attention_heads": 20, "decoder_ffn_dim": 5120, "decoder_layerdrop": 0.0, "decoder_layers": 32, "decoder_start_token_id": 50258, "dropout": 0.0, "encoder_attention_heads": 20, "encoder_ffn_dim": 5120, "encoder_layerdrop": 0.0, "encoder_layers": 32, "eos_token_id": 50257, "forced_decoder_ids": [[1, 50259], [2, 50359], [3, 50363]], "init_std": 0.02, "is_encoder_decoder": true, "max_length": 448, "max_source_positions": 1500, "max_target_positions": 448, "model_type": "whisper", "num_hidden_layers": 32, "num_mel_bins": 80, "pad_token_id": 50257, "scale_embedding": false, "suppress_tokens": [1, 2, 7, 8, 9, 10, 14, 25, 26, 27, 28, 29, 31, 58, 59, 60, 61, 62, 63, 90, 91, 92, 93, 359, 503, 522, 542, 873, 893, 902, 918, 922, 931, 1350, 1853, 1982, 2460, 2627, 3246, 3253, 3268, 3536, 3846, 3961, 4183, 4667, 6585, 6647, 7273, 9061, 9383, 10428, 10929, 11938, 12033, 12331, 12562, 13793, 14157, 14635, 15265, 15618, 16553, 16604, 18362, 18956, 20075, 21675, 22520, 26130, 26161, 26435, 28279, 29464, 31650, 32302, 32470, 36865, 42863, 47425, 49870, 50254, 50258, 50358, 50359, 50360, 50361, 50362], "torch_dtype": "float32", "transformers_version": "4.27.0.dev0", "use_cache": true, "vocab_size": 51865}

openai_whisper-large-v2_turbo_1022MB/generation_config.json

@@ -1 +0,0 @@
-{"alignment_heads": [[10, 12], [13, 17], [16, 11], [16, 12], [16, 13], [17, 15], [17, 16], [18, 4], [18, 11], [18, 19], [19, 11], [21, 2], [21, 3], [22, 3], [22, 9], [22, 12], [23, 5], [23, 7], [23, 13], [25, 5], [26, 1], [26, 12], [27, 15]], "begin_suppress_tokens": [220, 50257], "bos_token_id": 50257, "decoder_start_token_id": 50258, "eos_token_id": 50257, "forced_decoder_ids": [[1, null], [2, 50359]], "is_multilingual": true, "lang_to_id": {"<|af|>": 50327, "<|am|>": 50334, "<|ar|>": 50272, "<|as|>": 50350, "<|az|>": 50304, "<|ba|>": 50355, "<|be|>": 50330, "<|bg|>": 50292, "<|bn|>": 50302, "<|bo|>": 50347, "<|br|>": 50309, "<|bs|>": 50315, "<|ca|>": 50270, "<|cs|>": 50283, "<|cy|>": 50297, "<|da|>": 50285, "<|de|>": 50261, "<|el|>": 50281, "<|en|>": 50259, "<|es|>": 50262, "<|et|>": 50307, "<|eu|>": 50310, "<|fa|>": 50300, "<|fi|>": 50277, "<|fo|>": 50338, "<|fr|>": 50265, "<|gl|>": 50319, "<|gu|>": 50333, "<|haw|>": 50352, "<|ha|>": 50354, "<|he|>": 50279, "<|hi|>": 50276, "<|hr|>": 50291, "<|ht|>": 50339, "<|hu|>": 50286, "<|hy|>": 50312, "<|id|>": 50275, "<|is|>": 50311, "<|it|>": 50274, "<|ja|>": 50266, "<|jw|>": 50356, "<|ka|>": 50329, "<|kk|>": 50316, "<|km|>": 50323, "<|kn|>": 50306, "<|ko|>": 50264, "<|la|>": 50294, "<|lb|>": 50345, "<|ln|>": 50353, "<|lo|>": 50336, "<|lt|>": 50293, "<|lv|>": 50301, "<|mg|>": 50349, "<|mi|>": 50295, "<|mk|>": 50308, "<|ml|>": 50296, "<|mn|>": 50314, "<|mr|>": 50320, "<|ms|>": 50282, "<|mt|>": 50343, "<|my|>": 50346, "<|ne|>": 50313, "<|nl|>": 50271, "<|nn|>": 50342, "<|no|>": 50288, "<|oc|>": 50328, "<|pa|>": 50321, "<|pl|>": 50269, "<|ps|>": 50340, "<|pt|>": 50267, "<|ro|>": 50284, "<|ru|>": 50263, "<|sa|>": 50344, "<|sd|>": 50332, "<|si|>": 50322, "<|sk|>": 50298, "<|sl|>": 50305, "<|sn|>": 50324, "<|so|>": 50326, "<|sq|>": 50317, "<|sr|>": 50303, "<|su|>": 50357, "<|sv|>": 50273, "<|sw|>": 50318, "<|ta|>": 50287, "<|te|>": 50299, "<|tg|>": 50331, "<|th|>": 50289, "<|tk|>": 50341, "<|tl|>": 50348, "<|tr|>": 50268, "<|tt|>": 50351, "<|uk|>": 50280, "<|ur|>": 50290, "<|uz|>": 50337, "<|vi|>": 50278, "<|yi|>": 50335, "<|yo|>": 50325, "<|zh|>": 50260}, "max_initial_timestamp_index": 50, "max_length": 448, "no_timestamps_token_id": 50363, "pad_token_id": 50257, "prev_sot_token_id": 50361, "return_timestamps": false, "suppress_tokens": [1, 2, 7, 8, 9, 10, 14, 25, 26, 27, 28, 29, 31, 58, 59, 60, 61, 62, 63, 90, 91, 92, 93, 359, 503, 522, 542, 873, 893, 902, 918, 922, 931, 1350, 1853, 1982, 2460, 2627, 3246, 3253, 3268, 3536, 3846, 3961, 4183, 4667, 6585, 6647, 7273, 9061, 9383, 10428, 10929, 11938, 12033, 12331, 12562, 13793, 14157, 14635, 15265, 15618, 16553, 16604, 18362, 18956, 20075, 21675, 22520, 26130, 26161, 26435, 28279, 29464, 31650, 32302, 32470, 36865, 42863, 47425, 49870, 50254, 50258, 50358, 50359, 50360, 50361, 50362], "task_to_id": {"transcribe": 50359, "translate": 50358}, "transformers_version": "4.31.0.dev0"}

openai_whisper-large-v3_turbo_1018MB/AudioEncoder.mlmodelc/analytics/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:991dd4456033ffcdc497de0ee0b3c3e0497db076af562e61b29582e875d2d983
-size 243

openai_whisper-large-v3_turbo_1018MB/AudioEncoder.mlmodelc/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cb664c4d1bad4718501aec8ce5a850f1711dfd44f9bbbb26174191d670f78963
-size 348

openai_whisper-large-v3_turbo_1018MB/AudioEncoder.mlmodelc/metadata.json

@@ -1,70 +0,0 @@
-[
-  {
-    "metadataOutputVersion" : "3.0",
-    "storagePrecision" : "Mixed (Float16, Palettized (4 bits))",
-    "outputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 1280 × 1 × 1500)",
-        "shortDescription" : "",
-        "shape" : "[1, 1280, 1, 1500]",
-        "name" : "encoder_output_embeds",
-        "type" : "MultiArray"
-      }
-    ],
-    "modelParameters" : [
-
-    ],
-    "specificationVersion" : 8,
-    "mlProgramOperationTypeHistogram" : {
-      "Ios17.mul" : 2690,
-      "Ios17.transpose" : 32,
-      "Ios17.rsqrt" : 65,
-      "Ios16.constexprLutToDense" : 183,
-      "Ios17.conv" : 194,
-      "Ios17.sub" : 65,
-      "Ios16.einsum" : 5120,
-      "Ios17.concat" : 672,
-      "Ios17.add" : 130,
-      "Ios16.reduceMean" : 130,
-      "Ios17.batchNorm" : 65,
-      "Ios17.sliceByIndex" : 4480,
-      "Ios16.softmax" : 2560,
-      "Ios16.gelu" : 34
-    },
-    "computePrecision" : "Mixed (Float16, Float32, Int32)",
-    "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"
-    },
-    "userDefinedMetadata" : {
-      "com.github.apple.coremltools.source_dialect" : "TorchScript",
-      "com.github.apple.coremltools.source" : "torch==2.1.2",
-      "com.github.apple.coremltools.version" : "7.1"
-    },
-    "inputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 128 × 1 × 3000)",
-        "shortDescription" : "",
-        "shape" : "[1, 128, 1, 3000]",
-        "name" : "melspectrogram_features",
-        "type" : "MultiArray"
-      }
-    ],
-    "generatedClassName" : "AudioEncoder_mixedBitPalettized_5_3_bit",
-    "method" : "predict"
-  }
-]

openai_whisper-large-v3_turbo_1018MB/AudioEncoder.mlmodelc/weights/weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d8ff6006e0a265817228ffcc7b5a795657fdac6c91a9a18ceba26c42c666da8c
-size 418753024

openai_whisper-large-v3_turbo_1018MB/MelSpectrogram.mlmodelc/analytics/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c62db425d53939b1f6de686a371c4c95588e74f00b2938366a8bffcf6f7cd7ce
-size 243

openai_whisper-large-v3_turbo_1018MB/MelSpectrogram.mlmodelc/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:20c21e0be617e29544a1a4a1457dc23fe698139f6233ddea886f297aa8dfe877
-size 329

openai_whisper-large-v3_turbo_1018MB/MelSpectrogram.mlmodelc/metadata.json

@@ -1,71 +0,0 @@
-[
-  {
-    "metadataOutputVersion" : "3.0",
-    "storagePrecision" : "Float16",
-    "outputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 128 × 1 × 3000)",
-        "shortDescription" : "",
-        "shape" : "[1, 128, 1, 3000]",
-        "name" : "melspectrogram_features",
-        "type" : "MultiArray"
-      }
-    ],
-    "modelParameters" : [
-
-    ],
-    "specificationVersion" : 8,
-    "mlProgramOperationTypeHistogram" : {
-      "Ios17.mul" : 2,
-      "Ios17.sub" : 1,
-      "Ios17.matmul" : 1,
-      "Ios17.conv" : 2,
-      "Ios17.log" : 1,
-      "Ios17.add" : 3,
-      "Ios16.square" : 2,
-      "Ios17.sliceByIndex" : 1,
-      "Ios17.expandDims" : 4,
-      "Ios17.maximum" : 1,
-      "Ios16.reduceMax" : 1,
-      "Ios17.squeeze" : 2,
-      "Ios17.reshape" : 2,
-      "Identity" : 1,
-      "Pad" : 1
-    },
-    "computePrecision" : "Mixed (Float16, Float32, Int32)",
-    "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"
-    },
-    "userDefinedMetadata" : {
-      "com.github.apple.coremltools.source_dialect" : "TorchScript",
-      "com.github.apple.coremltools.source" : "torch==2.2.0",
-      "com.github.apple.coremltools.version" : "7.1"
-    },
-    "inputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 480000)",
-        "shortDescription" : "",
-        "shape" : "[480000]",
-        "name" : "audio",
-        "type" : "MultiArray"
-      }
-    ],
-    "generatedClassName" : "MelSpectrogram",
-    "method" : "predict"
-  }
-]

openai_whisper-large-v3_turbo_1018MB/MelSpectrogram.mlmodelc/model.mil

@@ -1,66 +0,0 @@
-program(1.0)
-[buildInfo = dict<tensor<string, []>, tensor<string, []>>({{"coremlc-component-MIL", "5.33.5"}, {"coremlc-version", "1877.40.3"}, {"coremltools-component-torch", "2.2.0"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "7.1"}})]
-{
-    func main<ios17>(tensor<fp16, [480000]> audio) {
-            tensor<int32, [3]> var_10 = const()[name = tensor<string, []>("op_10"), val = tensor<int32, [3]>([1, 1, 480000])];
-            tensor<fp16, [1, 1, 480000]> input_1_cast_fp16 = reshape(shape = var_10, x = audio)[name = tensor<string, []>("input_1_cast_fp16")];
-            tensor<int32, [6]> input_3_pad_0 = const()[name = tensor<string, []>("input_3_pad_0"), val = tensor<int32, [6]>([0, 0, 0, 0, 200, 200])];
-            tensor<string, []> input_3_mode_0 = const()[name = tensor<string, []>("input_3_mode_0"), val = tensor<string, []>("reflect")];
-            tensor<fp16, []> input_3_constant_val_0_to_fp16 = const()[name = tensor<string, []>("input_3_constant_val_0_to_fp16"), val = tensor<fp16, []>(0x0p+0)];
-            tensor<fp16, [1, 1, 480400]> input_3_cast_fp16 = pad(constant_val = input_3_constant_val_0_to_fp16, mode = input_3_mode_0, pad = input_3_pad_0, x = input_1_cast_fp16)[name = tensor<string, []>("input_3_cast_fp16")];
-            tensor<int32, [1]> var_22 = const()[name = tensor<string, []>("op_22"), val = tensor<int32, [1]>([480400])];
-            tensor<fp16, [480400]> input_cast_fp16 = reshape(shape = var_22, x = input_3_cast_fp16)[name = tensor<string, []>("input_cast_fp16")];
-            tensor<int32, [1]> expand_dims_0_axes_0 = const()[name = tensor<string, []>("expand_dims_0_axes_0"), val = tensor<int32, [1]>([0])];
-            tensor<fp16, [1, 480400]> expand_dims_0_cast_fp16 = expand_dims(axes = expand_dims_0_axes_0, x = input_cast_fp16)[name = tensor<string, []>("expand_dims_0_cast_fp16")];
-            tensor<int32, [1]> expand_dims_3 = const()[name = tensor<string, []>("expand_dims_3"), val = tensor<int32, [1]>([160])];
-            tensor<int32, [1]> expand_dims_4_axes_0 = const()[name = tensor<string, []>("expand_dims_4_axes_0"), val = tensor<int32, [1]>([1])];
-            tensor<fp16, [1, 1, 480400]> expand_dims_4_cast_fp16 = expand_dims(axes = expand_dims_4_axes_0, x = expand_dims_0_cast_fp16)[name = tensor<string, []>("expand_dims_4_cast_fp16")];
-            tensor<string, []> conv_0_pad_type_0 = const()[name = tensor<string, []>("conv_0_pad_type_0"), val = tensor<string, []>("valid")];
-            tensor<int32, [2]> conv_0_pad_0 = const()[name = tensor<string, []>("conv_0_pad_0"), val = tensor<int32, [2]>([0, 0])];
-            tensor<int32, [1]> conv_0_dilations_0 = const()[name = tensor<string, []>("conv_0_dilations_0"), val = tensor<int32, [1]>([1])];
-            tensor<int32, []> conv_0_groups_0 = const()[name = tensor<string, []>("conv_0_groups_0"), val = tensor<int32, []>(1)];
-            tensor<fp16, [201, 1, 400]> expand_dims_1_to_fp16 = const()[name = tensor<string, []>("expand_dims_1_to_fp16"), val = tensor<fp16, [201, 1, 400]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(64)))];
-            tensor<fp16, [1, 201, 3001]> conv_0_cast_fp16 = conv(dilations = conv_0_dilations_0, groups = conv_0_groups_0, pad = conv_0_pad_0, pad_type = conv_0_pad_type_0, strides = expand_dims_3, weight = expand_dims_1_to_fp16, x = expand_dims_4_cast_fp16)[name = tensor<string, []>("conv_0_cast_fp16")];
-            tensor<string, []> conv_1_pad_type_0 = const()[name = tensor<string, []>("conv_1_pad_type_0"), val = tensor<string, []>("valid")];
-            tensor<int32, [2]> conv_1_pad_0 = const()[name = tensor<string, []>("conv_1_pad_0"), val = tensor<int32, [2]>([0, 0])];
-            tensor<int32, [1]> conv_1_dilations_0 = const()[name = tensor<string, []>("conv_1_dilations_0"), val = tensor<int32, [1]>([1])];
-            tensor<int32, []> conv_1_groups_0 = const()[name = tensor<string, []>("conv_1_groups_0"), val = tensor<int32, []>(1)];
-            tensor<fp16, [201, 1, 400]> expand_dims_2_to_fp16 = const()[name = tensor<string, []>("expand_dims_2_to_fp16"), val = tensor<fp16, [201, 1, 400]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(160960)))];
-            tensor<fp16, [1, 201, 3001]> conv_1_cast_fp16 = conv(dilations = conv_1_dilations_0, groups = conv_1_groups_0, pad = conv_1_pad_0, pad_type = conv_1_pad_type_0, strides = expand_dims_3, weight = expand_dims_2_to_fp16, x = expand_dims_4_cast_fp16)[name = tensor<string, []>("conv_1_cast_fp16")];
-            tensor<int32, [1]> squeeze_0_axes_0 = const()[name = tensor<string, []>("squeeze_0_axes_0"), val = tensor<int32, [1]>([0])];
-            tensor<fp16, [201, 3001]> squeeze_0_cast_fp16 = squeeze(axes = squeeze_0_axes_0, x = conv_0_cast_fp16)[name = tensor<string, []>("squeeze_0_cast_fp16")];
-            tensor<int32, [1]> squeeze_1_axes_0 = const()[name = tensor<string, []>("squeeze_1_axes_0"), val = tensor<int32, [1]>([0])];
-            tensor<fp16, [201, 3001]> squeeze_1_cast_fp16 = squeeze(axes = squeeze_1_axes_0, x = conv_1_cast_fp16)[name = tensor<string, []>("squeeze_1_cast_fp16")];
-            tensor<fp16, [201, 3001]> square_0_cast_fp16 = square(x = squeeze_0_cast_fp16)[name = tensor<string, []>("square_0_cast_fp16")];
-            tensor<fp16, [201, 3001]> square_1_cast_fp16 = square(x = squeeze_1_cast_fp16)[name = tensor<string, []>("square_1_cast_fp16")];
-            tensor<fp16, [201, 3001]> add_1_cast_fp16 = add(x = square_0_cast_fp16, y = square_1_cast_fp16)[name = tensor<string, []>("add_1_cast_fp16")];
-            tensor<fp16, [201, 3001]> magnitudes_1_cast_fp16 = identity(x = add_1_cast_fp16)[name = tensor<string, []>("magnitudes_1_cast_fp16")];
-            tensor<int32, [2]> magnitudes_begin_0 = const()[name = tensor<string, []>("magnitudes_begin_0"), val = tensor<int32, [2]>([0, 0])];
-            tensor<int32, [2]> magnitudes_end_0 = const()[name = tensor<string, []>("magnitudes_end_0"), val = tensor<int32, [2]>([201, 3000])];
-            tensor<bool, [2]> magnitudes_end_mask_0 = const()[name = tensor<string, []>("magnitudes_end_mask_0"), val = tensor<bool, [2]>([true, false])];
-            tensor<fp16, [201, 3000]> magnitudes_cast_fp16 = slice_by_index(begin = magnitudes_begin_0, end = magnitudes_end_0, end_mask = magnitudes_end_mask_0, x = magnitudes_1_cast_fp16)[name = tensor<string, []>("magnitudes_cast_fp16")];
-            tensor<bool, []> mel_spec_1_transpose_x_0 = const()[name = tensor<string, []>("mel_spec_1_transpose_x_0"), val = tensor<bool, []>(false)];
-            tensor<bool, []> mel_spec_1_transpose_y_0 = const()[name = tensor<string, []>("mel_spec_1_transpose_y_0"), val = tensor<bool, []>(false)];
-            tensor<fp16, [128, 201]> mel_filters_to_fp16 = const()[name = tensor<string, []>("mel_filters_to_fp16"), val = tensor<fp16, [128, 201]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(321856)))];
-            tensor<fp16, [128, 3000]> mel_spec_1_cast_fp16 = matmul(transpose_x = mel_spec_1_transpose_x_0, transpose_y = mel_spec_1_transpose_y_0, x = mel_filters_to_fp16, y = magnitudes_cast_fp16)[name = tensor<string, []>("mel_spec_1_cast_fp16")];
-            tensor<fp16, []> var_41_to_fp16 = const()[name = tensor<string, []>("op_41_to_fp16"), val = tensor<fp16, []>(0x1p-24)];
-            tensor<fp16, [128, 3000]> mel_spec_cast_fp16 = add(x = mel_spec_1_cast_fp16, y = var_41_to_fp16)[name = tensor<string, []>("mel_spec_cast_fp16")];
-            tensor<fp32, []> log_0_epsilon_0 = const()[name = tensor<string, []>("log_0_epsilon_0"), val = tensor<fp32, []>(0x1p-149)];
-            tensor<fp16, [128, 3000]> log_0_cast_fp16 = log(epsilon = log_0_epsilon_0, x = mel_spec_cast_fp16)[name = tensor<string, []>("log_0_cast_fp16")];
-            tensor<fp16, []> mul_0_y_0_to_fp16 = const()[name = tensor<string, []>("mul_0_y_0_to_fp16"), val = tensor<fp16, []>(0x1.bccp-2)];
-            tensor<fp16, [128, 3000]> mul_0_cast_fp16 = mul(x = log_0_cast_fp16, y = mul_0_y_0_to_fp16)[name = tensor<string, []>("mul_0_cast_fp16")];
-            tensor<bool, []> var_44_keep_dims_0 = const()[name = tensor<string, []>("op_44_keep_dims_0"), val = tensor<bool, []>(false)];
-            tensor<fp16, []> var_44_cast_fp16 = reduce_max(keep_dims = var_44_keep_dims_0, x = mul_0_cast_fp16)[name = tensor<string, []>("op_44_cast_fp16")];
-            tensor<fp16, []> var_46_to_fp16 = const()[name = tensor<string, []>("op_46_to_fp16"), val = tensor<fp16, []>(0x1p+3)];
-            tensor<fp16, []> var_47_cast_fp16 = sub(x = var_44_cast_fp16, y = var_46_to_fp16)[name = tensor<string, []>("op_47_cast_fp16")];
-            tensor<fp16, [128, 3000]> log_spec_3_cast_fp16 = maximum(x = mul_0_cast_fp16, y = var_47_cast_fp16)[name = tensor<string, []>("log_spec_3_cast_fp16")];
-            tensor<fp16, []> var_50_to_fp16 = const()[name = tensor<string, []>("op_50_to_fp16"), val = tensor<fp16, []>(0x1p+2)];
-            tensor<fp16, [128, 3000]> var_51_cast_fp16 = add(x = log_spec_3_cast_fp16, y = var_50_to_fp16)[name = tensor<string, []>("op_51_cast_fp16")];
-            tensor<fp16, []> _inversed_log_spec_y_0_to_fp16 = const()[name = tensor<string, []>("_inversed_log_spec_y_0_to_fp16"), val = tensor<fp16, []>(0x1p-2)];
-            tensor<fp16, [128, 3000]> _inversed_log_spec_cast_fp16 = mul(x = var_51_cast_fp16, y = _inversed_log_spec_y_0_to_fp16)[name = tensor<string, []>("_inversed_log_spec_cast_fp16")];
-            tensor<int32, [1]> var_55_axes_0 = const()[name = tensor<string, []>("op_55_axes_0"), val = tensor<int32, [1]>([0])];
-            tensor<fp16, [1, 128, 3000]> var_55_cast_fp16 = expand_dims(axes = var_55_axes_0, x = _inversed_log_spec_cast_fp16)[name = tensor<string, []>("op_55_cast_fp16")];
-            tensor<int32, [1]> var_62_axes_0 = const()[name = tensor<string, []>("op_62_axes_0"), val = tensor<int32, [1]>([2])];
-            tensor<fp16, [1, 128, 1, 3000]> melspectrogram_features = expand_dims(axes = var_62_axes_0, x = var_55_cast_fp16)[name = tensor<string, []>("op_62_cast_fp16")];
-        } -> (melspectrogram_features);
-}

openai_whisper-large-v3_turbo_1018MB/MelSpectrogram.mlmodelc/weights/weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:402f105add06ab265df7bcfa9d4efca273f3fda50e1b45f742a7996b11afb360
-size 373376

openai_whisper-large-v3_turbo_1018MB/TextDecoder.mlmodelc/analytics/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:85a041db4c384bf459d1f2b6114e51fda1f9fb16c6c7f8eb32176c45f99c17df
-size 243