Commit
•
0c81194
1
Parent(s):
cb17052
Delete openai_whisper-large-v2_turbo_1022MB - turbo model generated without TextDecoderContextPrefill
Browse files- openai_whisper-large-v2_turbo_1022MB/AudioEncoder.mlmodelc/analytics/coremldata.bin +0 -3
- openai_whisper-large-v2_turbo_1022MB/AudioEncoder.mlmodelc/coremldata.bin +0 -3
- openai_whisper-large-v2_turbo_1022MB/AudioEncoder.mlmodelc/metadata.json +0 -70
- openai_whisper-large-v2_turbo_1022MB/AudioEncoder.mlmodelc/model.mil +0 -0
- openai_whisper-large-v2_turbo_1022MB/AudioEncoder.mlmodelc/weights/weight.bin +0 -3
- openai_whisper-large-v2_turbo_1022MB/MelSpectrogram.mlmodelc/analytics/coremldata.bin +0 -3
- openai_whisper-large-v2_turbo_1022MB/MelSpectrogram.mlmodelc/coremldata.bin +0 -3
- openai_whisper-large-v2_turbo_1022MB/MelSpectrogram.mlmodelc/metadata.json +0 -71
- openai_whisper-large-v2_turbo_1022MB/MelSpectrogram.mlmodelc/model.mil +0 -66
- openai_whisper-large-v2_turbo_1022MB/MelSpectrogram.mlmodelc/weights/weight.bin +0 -3
- openai_whisper-large-v2_turbo_1022MB/TextDecoder.mlmodelc/analytics/coremldata.bin +0 -3
- openai_whisper-large-v2_turbo_1022MB/TextDecoder.mlmodelc/coremldata.bin +0 -3
- openai_whisper-large-v2_turbo_1022MB/TextDecoder.mlmodelc/metadata.json +0 -156
- openai_whisper-large-v2_turbo_1022MB/TextDecoder.mlmodelc/model.mil +0 -0
- openai_whisper-large-v2_turbo_1022MB/TextDecoder.mlmodelc/weights/weight.bin +0 -3
- openai_whisper-large-v2_turbo_1022MB/config.json +0 -1
- openai_whisper-large-v2_turbo_1022MB/generation_config.json +0 -1
openai_whisper-large-v2_turbo_1022MB/AudioEncoder.mlmodelc/analytics/coremldata.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:246bfd29afc3ea7c5e225152469442ffe4064236c3cd9b9c66872c7cf4ac2c72
|
3 |
-
size 243
|
|
|
|
|
|
|
|
openai_whisper-large-v2_turbo_1022MB/AudioEncoder.mlmodelc/coremldata.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:e30541466a5715be01aa4874597a0c84b827f1d5377cbe89e379bd6f369e851e
|
3 |
-
size 347
|
|
|
|
|
|
|
|
openai_whisper-large-v2_turbo_1022MB/AudioEncoder.mlmodelc/metadata.json
DELETED
@@ -1,70 +0,0 @@
|
|
1 |
-
[
|
2 |
-
{
|
3 |
-
"metadataOutputVersion" : "3.0",
|
4 |
-
"storagePrecision" : "Mixed (Float16, Palettized (4 bits))",
|
5 |
-
"outputSchema" : [
|
6 |
-
{
|
7 |
-
"hasShapeFlexibility" : "0",
|
8 |
-
"isOptional" : "0",
|
9 |
-
"dataType" : "Float16",
|
10 |
-
"formattedType" : "MultiArray (Float16 1 × 1280 × 1 × 1500)",
|
11 |
-
"shortDescription" : "",
|
12 |
-
"shape" : "[1, 1280, 1, 1500]",
|
13 |
-
"name" : "encoder_output_embeds",
|
14 |
-
"type" : "MultiArray"
|
15 |
-
}
|
16 |
-
],
|
17 |
-
"modelParameters" : [
|
18 |
-
|
19 |
-
],
|
20 |
-
"specificationVersion" : 8,
|
21 |
-
"mlProgramOperationTypeHistogram" : {
|
22 |
-
"Ios17.mul" : 2690,
|
23 |
-
"Ios17.transpose" : 32,
|
24 |
-
"Ios17.rsqrt" : 65,
|
25 |
-
"Ios16.constexprLutToDense" : 182,
|
26 |
-
"Ios17.conv" : 194,
|
27 |
-
"Ios17.sub" : 65,
|
28 |
-
"Ios16.einsum" : 5120,
|
29 |
-
"Ios17.concat" : 672,
|
30 |
-
"Ios17.add" : 130,
|
31 |
-
"Ios16.reduceMean" : 130,
|
32 |
-
"Ios17.batchNorm" : 65,
|
33 |
-
"Ios17.sliceByIndex" : 4480,
|
34 |
-
"Ios16.softmax" : 2560,
|
35 |
-
"Ios16.gelu" : 34
|
36 |
-
},
|
37 |
-
"computePrecision" : "Mixed (Float16, Float32, Int32)",
|
38 |
-
"isUpdatable" : "0",
|
39 |
-
"availability" : {
|
40 |
-
"macOS" : "14.0",
|
41 |
-
"tvOS" : "17.0",
|
42 |
-
"visionOS" : "1.0",
|
43 |
-
"watchOS" : "10.0",
|
44 |
-
"iOS" : "17.0",
|
45 |
-
"macCatalyst" : "17.0"
|
46 |
-
},
|
47 |
-
"modelType" : {
|
48 |
-
"name" : "MLModelType_mlProgram"
|
49 |
-
},
|
50 |
-
"userDefinedMetadata" : {
|
51 |
-
"com.github.apple.coremltools.source_dialect" : "TorchScript",
|
52 |
-
"com.github.apple.coremltools.source" : "torch==2.1.2",
|
53 |
-
"com.github.apple.coremltools.version" : "7.1"
|
54 |
-
},
|
55 |
-
"inputSchema" : [
|
56 |
-
{
|
57 |
-
"hasShapeFlexibility" : "0",
|
58 |
-
"isOptional" : "0",
|
59 |
-
"dataType" : "Float16",
|
60 |
-
"formattedType" : "MultiArray (Float16 1 × 80 × 1 × 3000)",
|
61 |
-
"shortDescription" : "",
|
62 |
-
"shape" : "[1, 80, 1, 3000]",
|
63 |
-
"name" : "melspectrogram_features",
|
64 |
-
"type" : "MultiArray"
|
65 |
-
}
|
66 |
-
],
|
67 |
-
"generatedClassName" : "AudioEncoder_mixedBitPalettized_5_3_bit",
|
68 |
-
"method" : "predict"
|
69 |
-
}
|
70 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
openai_whisper-large-v2_turbo_1022MB/AudioEncoder.mlmodelc/model.mil
DELETED
The diff for this file is too large to render.
See raw diff
|
|
openai_whisper-large-v2_turbo_1022MB/AudioEncoder.mlmodelc/weights/weight.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:5998c3da8d47af4ce963c3905a072ee4eebf181610ea3a1a27cd682f138d052b
|
3 |
-
size 420841856
|
|
|
|
|
|
|
|
openai_whisper-large-v2_turbo_1022MB/MelSpectrogram.mlmodelc/analytics/coremldata.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:b065e1f3f876bc8dc2e67df6d54d8433a2352afca63e0aa986bb0080797a6164
|
3 |
-
size 243
|
|
|
|
|
|
|
|
openai_whisper-large-v2_turbo_1022MB/MelSpectrogram.mlmodelc/coremldata.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:95769e69794de49c2f2d0fa44b99605449f7259ff804161a0e01afc74a9fa5ef
|
3 |
-
size 328
|
|
|
|
|
|
|
|
openai_whisper-large-v2_turbo_1022MB/MelSpectrogram.mlmodelc/metadata.json
DELETED
@@ -1,71 +0,0 @@
|
|
1 |
-
[
|
2 |
-
{
|
3 |
-
"metadataOutputVersion" : "3.0",
|
4 |
-
"storagePrecision" : "Float16",
|
5 |
-
"outputSchema" : [
|
6 |
-
{
|
7 |
-
"hasShapeFlexibility" : "0",
|
8 |
-
"isOptional" : "0",
|
9 |
-
"dataType" : "Float16",
|
10 |
-
"formattedType" : "MultiArray (Float16 1 × 80 × 1 × 3000)",
|
11 |
-
"shortDescription" : "",
|
12 |
-
"shape" : "[1, 80, 1, 3000]",
|
13 |
-
"name" : "melspectrogram_features",
|
14 |
-
"type" : "MultiArray"
|
15 |
-
}
|
16 |
-
],
|
17 |
-
"modelParameters" : [
|
18 |
-
|
19 |
-
],
|
20 |
-
"specificationVersion" : 8,
|
21 |
-
"mlProgramOperationTypeHistogram" : {
|
22 |
-
"Ios17.mul" : 2,
|
23 |
-
"Ios17.sub" : 1,
|
24 |
-
"Ios17.matmul" : 1,
|
25 |
-
"Ios17.conv" : 2,
|
26 |
-
"Ios17.log" : 1,
|
27 |
-
"Ios17.add" : 3,
|
28 |
-
"Ios16.square" : 2,
|
29 |
-
"Ios17.sliceByIndex" : 1,
|
30 |
-
"Ios17.expandDims" : 4,
|
31 |
-
"Ios17.maximum" : 1,
|
32 |
-
"Ios16.reduceMax" : 1,
|
33 |
-
"Ios17.squeeze" : 2,
|
34 |
-
"Ios17.reshape" : 2,
|
35 |
-
"Identity" : 1,
|
36 |
-
"Pad" : 1
|
37 |
-
},
|
38 |
-
"computePrecision" : "Mixed (Float16, Float32, Int32)",
|
39 |
-
"isUpdatable" : "0",
|
40 |
-
"availability" : {
|
41 |
-
"macOS" : "14.0",
|
42 |
-
"tvOS" : "17.0",
|
43 |
-
"visionOS" : "1.0",
|
44 |
-
"watchOS" : "10.0",
|
45 |
-
"iOS" : "17.0",
|
46 |
-
"macCatalyst" : "17.0"
|
47 |
-
},
|
48 |
-
"modelType" : {
|
49 |
-
"name" : "MLModelType_mlProgram"
|
50 |
-
},
|
51 |
-
"userDefinedMetadata" : {
|
52 |
-
"com.github.apple.coremltools.source_dialect" : "TorchScript",
|
53 |
-
"com.github.apple.coremltools.source" : "torch==2.1.2",
|
54 |
-
"com.github.apple.coremltools.version" : "7.1"
|
55 |
-
},
|
56 |
-
"inputSchema" : [
|
57 |
-
{
|
58 |
-
"hasShapeFlexibility" : "0",
|
59 |
-
"isOptional" : "0",
|
60 |
-
"dataType" : "Float16",
|
61 |
-
"formattedType" : "MultiArray (Float16 480000)",
|
62 |
-
"shortDescription" : "",
|
63 |
-
"shape" : "[480000]",
|
64 |
-
"name" : "audio",
|
65 |
-
"type" : "MultiArray"
|
66 |
-
}
|
67 |
-
],
|
68 |
-
"generatedClassName" : "MelSpectrogram",
|
69 |
-
"method" : "predict"
|
70 |
-
}
|
71 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
openai_whisper-large-v2_turbo_1022MB/MelSpectrogram.mlmodelc/model.mil
DELETED
@@ -1,66 +0,0 @@
|
|
1 |
-
program(1.0)
|
2 |
-
[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"}})]
|
3 |
-
{
|
4 |
-
func main<ios17>(tensor<fp16, [480000]> audio) {
|
5 |
-
tensor<int32, [3]> var_10 = const()[name = tensor<string, []>("op_10"), val = tensor<int32, [3]>([1, 1, 480000])];
|
6 |
-
tensor<fp16, [1, 1, 480000]> var_11_cast_fp16 = reshape(shape = var_10, x = audio)[name = tensor<string, []>("op_11_cast_fp16")];
|
7 |
-
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])];
|
8 |
-
tensor<string, []> input_1_mode_0 = const()[name = tensor<string, []>("input_1_mode_0"), val = tensor<string, []>("reflect")];
|
9 |
-
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)];
|
10 |
-
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")];
|
11 |
-
tensor<int32, [1]> var_22 = const()[name = tensor<string, []>("op_22"), val = tensor<int32, [1]>([480400])];
|
12 |
-
tensor<fp16, [480400]> input_cast_fp16 = reshape(shape = var_22, x = input_1_cast_fp16)[name = tensor<string, []>("input_cast_fp16")];
|
13 |
-
tensor<int32, [1]> expand_dims_0_axes_0 = const()[name = tensor<string, []>("expand_dims_0_axes_0"), val = tensor<int32, [1]>([0])];
|
14 |
-
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")];
|
15 |
-
tensor<int32, [1]> expand_dims_3 = const()[name = tensor<string, []>("expand_dims_3"), val = tensor<int32, [1]>([160])];
|
16 |
-
tensor<int32, [1]> expand_dims_4_axes_0 = const()[name = tensor<string, []>("expand_dims_4_axes_0"), val = tensor<int32, [1]>([1])];
|
17 |
-
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")];
|
18 |
-
tensor<string, []> conv_0_pad_type_0 = const()[name = tensor<string, []>("conv_0_pad_type_0"), val = tensor<string, []>("valid")];
|
19 |
-
tensor<int32, [2]> conv_0_pad_0 = const()[name = tensor<string, []>("conv_0_pad_0"), val = tensor<int32, [2]>([0, 0])];
|
20 |
-
tensor<int32, [1]> conv_0_dilations_0 = const()[name = tensor<string, []>("conv_0_dilations_0"), val = tensor<int32, [1]>([1])];
|
21 |
-
tensor<int32, []> conv_0_groups_0 = const()[name = tensor<string, []>("conv_0_groups_0"), val = tensor<int32, []>(1)];
|
22 |
-
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)))];
|
23 |
-
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")];
|
24 |
-
tensor<string, []> conv_1_pad_type_0 = const()[name = tensor<string, []>("conv_1_pad_type_0"), val = tensor<string, []>("valid")];
|
25 |
-
tensor<int32, [2]> conv_1_pad_0 = const()[name = tensor<string, []>("conv_1_pad_0"), val = tensor<int32, [2]>([0, 0])];
|
26 |
-
tensor<int32, [1]> conv_1_dilations_0 = const()[name = tensor<string, []>("conv_1_dilations_0"), val = tensor<int32, [1]>([1])];
|
27 |
-
tensor<int32, []> conv_1_groups_0 = const()[name = tensor<string, []>("conv_1_groups_0"), val = tensor<int32, []>(1)];
|
28 |
-
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)))];
|
29 |
-
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")];
|
30 |
-
tensor<int32, [1]> squeeze_0_axes_0 = const()[name = tensor<string, []>("squeeze_0_axes_0"), val = tensor<int32, [1]>([0])];
|
31 |
-
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")];
|
32 |
-
tensor<int32, [1]> squeeze_1_axes_0 = const()[name = tensor<string, []>("squeeze_1_axes_0"), val = tensor<int32, [1]>([0])];
|
33 |
-
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")];
|
34 |
-
tensor<fp16, [201, 3001]> square_0_cast_fp16 = square(x = squeeze_0_cast_fp16)[name = tensor<string, []>("square_0_cast_fp16")];
|
35 |
-
tensor<fp16, [201, 3001]> square_1_cast_fp16 = square(x = squeeze_1_cast_fp16)[name = tensor<string, []>("square_1_cast_fp16")];
|
36 |
-
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")];
|
37 |
-
tensor<fp16, [201, 3001]> magnitudes_1_cast_fp16 = identity(x = add_1_cast_fp16)[name = tensor<string, []>("magnitudes_1_cast_fp16")];
|
38 |
-
tensor<int32, [2]> magnitudes_begin_0 = const()[name = tensor<string, []>("magnitudes_begin_0"), val = tensor<int32, [2]>([0, 0])];
|
39 |
-
tensor<int32, [2]> magnitudes_end_0 = const()[name = tensor<string, []>("magnitudes_end_0"), val = tensor<int32, [2]>([201, 3000])];
|
40 |
-
tensor<bool, [2]> magnitudes_end_mask_0 = const()[name = tensor<string, []>("magnitudes_end_mask_0"), val = tensor<bool, [2]>([true, false])];
|
41 |
-
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")];
|
42 |
-
tensor<bool, []> mel_spec_1_transpose_x_0 = const()[name = tensor<string, []>("mel_spec_1_transpose_x_0"), val = tensor<bool, []>(false)];
|
43 |
-
tensor<bool, []> mel_spec_1_transpose_y_0 = const()[name = tensor<string, []>("mel_spec_1_transpose_y_0"), val = tensor<bool, []>(false)];
|
44 |
-
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)))];
|
45 |
-
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")];
|
46 |
-
tensor<fp16, []> var_41_to_fp16 = const()[name = tensor<string, []>("op_41_to_fp16"), val = tensor<fp16, []>(0x1p-24)];
|
47 |
-
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")];
|
48 |
-
tensor<fp32, []> log_0_epsilon_0 = const()[name = tensor<string, []>("log_0_epsilon_0"), val = tensor<fp32, []>(0x1p-149)];
|
49 |
-
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")];
|
50 |
-
tensor<fp16, []> mul_0_y_0_to_fp16 = const()[name = tensor<string, []>("mul_0_y_0_to_fp16"), val = tensor<fp16, []>(0x1.bccp-2)];
|
51 |
-
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")];
|
52 |
-
tensor<bool, []> var_44_keep_dims_0 = const()[name = tensor<string, []>("op_44_keep_dims_0"), val = tensor<bool, []>(false)];
|
53 |
-
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")];
|
54 |
-
tensor<fp16, []> var_46_to_fp16 = const()[name = tensor<string, []>("op_46_to_fp16"), val = tensor<fp16, []>(0x1p+3)];
|
55 |
-
tensor<fp16, []> var_47_cast_fp16 = sub(x = var_44_cast_fp16, y = var_46_to_fp16)[name = tensor<string, []>("op_47_cast_fp16")];
|
56 |
-
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")];
|
57 |
-
tensor<fp16, []> var_50_to_fp16 = const()[name = tensor<string, []>("op_50_to_fp16"), val = tensor<fp16, []>(0x1p+2)];
|
58 |
-
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")];
|
59 |
-
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)];
|
60 |
-
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")];
|
61 |
-
tensor<int32, [1]> var_55_axes_0 = const()[name = tensor<string, []>("op_55_axes_0"), val = tensor<int32, [1]>([0])];
|
62 |
-
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")];
|
63 |
-
tensor<int32, [1]> var_62_axes_0 = const()[name = tensor<string, []>("op_62_axes_0"), val = tensor<int32, [1]>([2])];
|
64 |
-
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")];
|
65 |
-
} -> (melspectrogram_features);
|
66 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
openai_whisper-large-v2_turbo_1022MB/MelSpectrogram.mlmodelc/weights/weight.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:707270213d25adca3dbe86f655d1869d9ef238a8701c518051a9fc362f2767cf
|
3 |
-
size 354080
|
|
|
|
|
|
|
|
openai_whisper-large-v2_turbo_1022MB/TextDecoder.mlmodelc/analytics/coremldata.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:fa29f227123e4ef9158ceef783082d9d4b6d29983146fba4ea8374a5c3210ecc
|
3 |
-
size 243
|
|
|
|
|
|
|
|
openai_whisper-large-v2_turbo_1022MB/TextDecoder.mlmodelc/coremldata.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:5f1241f3ff2552f8624a8bbfe55406467d80d13da19af518f2ebc4041bbeafe5
|
3 |
-
size 597
|
|
|
|
|
|
|
|
openai_whisper-large-v2_turbo_1022MB/TextDecoder.mlmodelc/metadata.json
DELETED
@@ -1,156 +0,0 @@
|
|
1 |
-
[
|
2 |
-
{
|
3 |
-
"metadataOutputVersion" : "3.0",
|
4 |
-
"storagePrecision" : "Mixed (Float16, Palettized (4 bits), Palettized (6 bits))",
|
5 |
-
"outputSchema" : [
|
6 |
-
{
|
7 |
-
"hasShapeFlexibility" : "0",
|
8 |
-
"isOptional" : "0",
|
9 |
-
"dataType" : "Float16",
|
10 |
-
"formattedType" : "MultiArray (Float16 1 × 1 × 51865)",
|
11 |
-
"shortDescription" : "",
|
12 |
-
"shape" : "[1, 1, 51865]",
|
13 |
-
"name" : "logits",
|
14 |
-
"type" : "MultiArray"
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"hasShapeFlexibility" : "0",
|
18 |
-
"isOptional" : "0",
|
19 |
-
"dataType" : "Float16",
|
20 |
-
"formattedType" : "MultiArray (Float16 1 × 40960 × 1 × 1)",
|
21 |
-
"shortDescription" : "",
|
22 |
-
"shape" : "[1, 40960, 1, 1]",
|
23 |
-
"name" : "key_cache_updates",
|
24 |
-
"type" : "MultiArray"
|
25 |
-
},
|
26 |
-
{
|
27 |
-
"hasShapeFlexibility" : "0",
|
28 |
-
"isOptional" : "0",
|
29 |
-
"dataType" : "Float16",
|
30 |
-
"formattedType" : "MultiArray (Float16 1 × 40960 × 1 × 1)",
|
31 |
-
"shortDescription" : "",
|
32 |
-
"shape" : "[1, 40960, 1, 1]",
|
33 |
-
"name" : "value_cache_updates",
|
34 |
-
"type" : "MultiArray"
|
35 |
-
}
|
36 |
-
],
|
37 |
-
"modelParameters" : [
|
38 |
-
|
39 |
-
],
|
40 |
-
"specificationVersion" : 8,
|
41 |
-
"mlProgramOperationTypeHistogram" : {
|
42 |
-
"Ios17.reshape" : 256,
|
43 |
-
"Ios16.reduceMean" : 194,
|
44 |
-
"Ios16.softmax" : 64,
|
45 |
-
"Ios17.matmul" : 128,
|
46 |
-
"Ios17.transpose" : 1,
|
47 |
-
"Split" : 2,
|
48 |
-
"Ios17.expandDims" : 6,
|
49 |
-
"Ios17.add" : 610,
|
50 |
-
"Ios17.squeeze" : 1,
|
51 |
-
"Ios17.gather" : 2,
|
52 |
-
"Ios17.batchNorm" : 97,
|
53 |
-
"Ios16.gelu" : 32,
|
54 |
-
"Ios17.cast" : 1,
|
55 |
-
"Ios16.constexprLutToDense" : 320,
|
56 |
-
"Ios17.conv" : 960,
|
57 |
-
"Ios17.sub" : 98,
|
58 |
-
"Ios17.concat" : 2,
|
59 |
-
"Ios17.linear" : 1,
|
60 |
-
"Ios17.rsqrt" : 97,
|
61 |
-
"Ios17.mul" : 386
|
62 |
-
},
|
63 |
-
"computePrecision" : "Mixed (Float16, Float32, Int16, Int32)",
|
64 |
-
"isUpdatable" : "0",
|
65 |
-
"availability" : {
|
66 |
-
"macOS" : "14.0",
|
67 |
-
"tvOS" : "17.0",
|
68 |
-
"visionOS" : "1.0",
|
69 |
-
"watchOS" : "10.0",
|
70 |
-
"iOS" : "17.0",
|
71 |
-
"macCatalyst" : "17.0"
|
72 |
-
},
|
73 |
-
"modelType" : {
|
74 |
-
"name" : "MLModelType_mlProgram"
|
75 |
-
},
|
76 |
-
"userDefinedMetadata" : {
|
77 |
-
"com.github.apple.coremltools.source_dialect" : "TorchScript",
|
78 |
-
"com.github.apple.coremltools.source" : "torch==2.2.0",
|
79 |
-
"com.github.apple.coremltools.version" : "7.1"
|
80 |
-
},
|
81 |
-
"inputSchema" : [
|
82 |
-
{
|
83 |
-
"hasShapeFlexibility" : "0",
|
84 |
-
"isOptional" : "0",
|
85 |
-
"dataType" : "Int32",
|
86 |
-
"formattedType" : "MultiArray (Int32 1)",
|
87 |
-
"shortDescription" : "",
|
88 |
-
"shape" : "[1]",
|
89 |
-
"name" : "input_ids",
|
90 |
-
"type" : "MultiArray"
|
91 |
-
},
|
92 |
-
{
|
93 |
-
"hasShapeFlexibility" : "0",
|
94 |
-
"isOptional" : "0",
|
95 |
-
"dataType" : "Int32",
|
96 |
-
"formattedType" : "MultiArray (Int32 1)",
|
97 |
-
"shortDescription" : "",
|
98 |
-
"shape" : "[1]",
|
99 |
-
"name" : "cache_length",
|
100 |
-
"type" : "MultiArray"
|
101 |
-
},
|
102 |
-
{
|
103 |
-
"hasShapeFlexibility" : "0",
|
104 |
-
"isOptional" : "0",
|
105 |
-
"dataType" : "Float16",
|
106 |
-
"formattedType" : "MultiArray (Float16 1 × 40960 × 1 × 448)",
|
107 |
-
"shortDescription" : "",
|
108 |
-
"shape" : "[1, 40960, 1, 448]",
|
109 |
-
"name" : "key_cache",
|
110 |
-
"type" : "MultiArray"
|
111 |
-
},
|
112 |
-
{
|
113 |
-
"hasShapeFlexibility" : "0",
|
114 |
-
"isOptional" : "0",
|
115 |
-
"dataType" : "Float16",
|
116 |
-
"formattedType" : "MultiArray (Float16 1 × 40960 × 1 × 448)",
|
117 |
-
"shortDescription" : "",
|
118 |
-
"shape" : "[1, 40960, 1, 448]",
|
119 |
-
"name" : "value_cache",
|
120 |
-
"type" : "MultiArray"
|
121 |
-
},
|
122 |
-
{
|
123 |
-
"hasShapeFlexibility" : "0",
|
124 |
-
"isOptional" : "0",
|
125 |
-
"dataType" : "Float16",
|
126 |
-
"formattedType" : "MultiArray (Float16 1 × 448)",
|
127 |
-
"shortDescription" : "",
|
128 |
-
"shape" : "[1, 448]",
|
129 |
-
"name" : "kv_cache_update_mask",
|
130 |
-
"type" : "MultiArray"
|
131 |
-
},
|
132 |
-
{
|
133 |
-
"hasShapeFlexibility" : "0",
|
134 |
-
"isOptional" : "0",
|
135 |
-
"dataType" : "Float16",
|
136 |
-
"formattedType" : "MultiArray (Float16 1 × 1280 × 1 × 1500)",
|
137 |
-
"shortDescription" : "",
|
138 |
-
"shape" : "[1, 1280, 1, 1500]",
|
139 |
-
"name" : "encoder_output_embeds",
|
140 |
-
"type" : "MultiArray"
|
141 |
-
},
|
142 |
-
{
|
143 |
-
"hasShapeFlexibility" : "0",
|
144 |
-
"isOptional" : "0",
|
145 |
-
"dataType" : "Float16",
|
146 |
-
"formattedType" : "MultiArray (Float16 1 × 448)",
|
147 |
-
"shortDescription" : "",
|
148 |
-
"shape" : "[1, 448]",
|
149 |
-
"name" : "decoder_key_padding_mask",
|
150 |
-
"type" : "MultiArray"
|
151 |
-
}
|
152 |
-
],
|
153 |
-
"generatedClassName" : "TextDecoder_mixedBitPalettized_4_0_bit",
|
154 |
-
"method" : "predict"
|
155 |
-
}
|
156 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
openai_whisper-large-v2_turbo_1022MB/TextDecoder.mlmodelc/model.mil
DELETED
The diff for this file is too large to render.
See raw diff
|
|
openai_whisper-large-v2_turbo_1022MB/TextDecoder.mlmodelc/weights/weight.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:7c2a8ea0d9d4cd3f2a5ba3d761cd609bdafb0edc2a35c11f1af0148af8be7103
|
3 |
-
size 592355826
|
|
|
|
|
|
|
|
openai_whisper-large-v2_turbo_1022MB/config.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"_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
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"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"}
|
|
|
|