alpaycli commited on
Commit
2b5d794
·
verified ·
1 Parent(s): 75bdaa4

Upload 25 files

Browse files
Files changed (25) hide show
  1. LocalDoc_azerbaijani-whisper-small/.DS_Store +0 -0
  2. LocalDoc_azerbaijani-whisper-small/AudioEncoder.mlcomputeplan.json +0 -0
  3. LocalDoc_azerbaijani-whisper-small/AudioEncoder.mlmodelc/analytics/coremldata.bin +3 -0
  4. LocalDoc_azerbaijani-whisper-small/AudioEncoder.mlmodelc/coremldata.bin +3 -0
  5. LocalDoc_azerbaijani-whisper-small/AudioEncoder.mlmodelc/metadata.json +71 -0
  6. LocalDoc_azerbaijani-whisper-small/AudioEncoder.mlmodelc/model.mil +0 -0
  7. LocalDoc_azerbaijani-whisper-small/AudioEncoder.mlmodelc/weights/weight.bin +3 -0
  8. LocalDoc_azerbaijani-whisper-small/MelSpectrogram.mlcomputeplan.json +199 -0
  9. LocalDoc_azerbaijani-whisper-small/MelSpectrogram.mlmodelc/analytics/coremldata.bin +3 -0
  10. LocalDoc_azerbaijani-whisper-small/MelSpectrogram.mlmodelc/coremldata.bin +3 -0
  11. LocalDoc_azerbaijani-whisper-small/MelSpectrogram.mlmodelc/metadata.json +75 -0
  12. LocalDoc_azerbaijani-whisper-small/MelSpectrogram.mlmodelc/model.mil +66 -0
  13. LocalDoc_azerbaijani-whisper-small/MelSpectrogram.mlmodelc/weights/weight.bin +3 -0
  14. LocalDoc_azerbaijani-whisper-small/TextDecoder.mlcomputeplan.json +0 -0
  15. LocalDoc_azerbaijani-whisper-small/TextDecoder.mlmodelc/analytics/coremldata.bin +3 -0
  16. LocalDoc_azerbaijani-whisper-small/TextDecoder.mlmodelc/coremldata.bin +3 -0
  17. LocalDoc_azerbaijani-whisper-small/TextDecoder.mlmodelc/metadata.json +169 -0
  18. LocalDoc_azerbaijani-whisper-small/TextDecoder.mlmodelc/model.mil +0 -0
  19. LocalDoc_azerbaijani-whisper-small/TextDecoder.mlmodelc/weights/weight.bin +3 -0
  20. LocalDoc_azerbaijani-whisper-small/config.json +59 -0
  21. LocalDoc_azerbaijani-whisper-small/coreml_manifest.json +21 -0
  22. LocalDoc_azerbaijani-whisper-small/decoder_prompt_az_transcribe.json +14 -0
  23. LocalDoc_azerbaijani-whisper-small/generation_config.json +264 -0
  24. LocalDoc_azerbaijani-whisper-small/tokenizer.json +0 -0
  25. LocalDoc_azerbaijani-whisper-small/tokenizer_config.json +127 -0
LocalDoc_azerbaijani-whisper-small/.DS_Store ADDED
Binary file (6.15 kB). View file
 
LocalDoc_azerbaijani-whisper-small/AudioEncoder.mlcomputeplan.json ADDED
The diff for this file is too large to render. See raw diff
 
LocalDoc_azerbaijani-whisper-small/AudioEncoder.mlmodelc/analytics/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0c9b345dc6bd03d2893c0cf1d0fe983eff1033eae63d71e4d417b69070b319c
3
+ size 243
LocalDoc_azerbaijani-whisper-small/AudioEncoder.mlmodelc/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aeda6c5e7031c1a6c1baf2fc1b1cf2e4015a73c54ac2f93036b23c76d8a8121
3
+ size 408
LocalDoc_azerbaijani-whisper-small/AudioEncoder.mlmodelc/metadata.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 × 768 × 1 × 1500)",
11
+ "shortDescription" : "",
12
+ "shape" : "[1, 768, 1, 1500]",
13
+ "name" : "encoder_output_embeds",
14
+ "type" : "MultiArray"
15
+ }
16
+ ],
17
+ "modelParameters" : [
18
+
19
+ ],
20
+ "specificationVersion" : 7,
21
+ "mlProgramOperationTypeHistogram" : {
22
+ "Concat" : 156,
23
+ "Ios16.add" : 25,
24
+ "Ios16.mul" : 864,
25
+ "SliceByIndex" : 1296,
26
+ "Transpose" : 12,
27
+ "Ios16.batchNorm" : 25,
28
+ "Ios16.gelu" : 14,
29
+ "Ios16.einsum" : 1728,
30
+ "Ios16.softmax" : 864,
31
+ "Ios16.layerNorm" : 25,
32
+ "Ios16.conv" : 74
33
+ },
34
+ "computePrecision" : "Mixed (Float16, Int32)",
35
+ "isUpdatable" : "0",
36
+ "stateSchema" : [
37
+
38
+ ],
39
+ "availability" : {
40
+ "macOS" : "13.0",
41
+ "tvOS" : "16.0",
42
+ "visionOS" : "1.0",
43
+ "watchOS" : "9.0",
44
+ "iOS" : "16.0",
45
+ "macCatalyst" : "16.0"
46
+ },
47
+ "modelType" : {
48
+ "name" : "MLModelType_mlProgram"
49
+ },
50
+ "userDefinedMetadata" : {
51
+ "com.github.apple.coremltools.conversion_date" : "2026-03-28",
52
+ "com.github.apple.coremltools.source" : "torch==2.2.2",
53
+ "com.github.apple.coremltools.version" : "9.0",
54
+ "com.github.apple.coremltools.source_dialect" : "TorchScript"
55
+ },
56
+ "inputSchema" : [
57
+ {
58
+ "hasShapeFlexibility" : "0",
59
+ "isOptional" : "0",
60
+ "dataType" : "Float16",
61
+ "formattedType" : "MultiArray (Float16 1 × 80 × 1 × 3000)",
62
+ "shortDescription" : "",
63
+ "shape" : "[1, 80, 1, 3000]",
64
+ "name" : "melspectrogram_features",
65
+ "type" : "MultiArray"
66
+ }
67
+ ],
68
+ "generatedClassName" : "AudioEncoder",
69
+ "method" : "predict"
70
+ }
71
+ ]
LocalDoc_azerbaijani-whisper-small/AudioEncoder.mlmodelc/model.mil ADDED
The diff for this file is too large to render. See raw diff
 
LocalDoc_azerbaijani-whisper-small/AudioEncoder.mlmodelc/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76fe62fb5721ab274c561e30b64d0b2542cc928a50ff4091714a30bbd55c23cd
3
+ size 176323456
LocalDoc_azerbaijani-whisper-small/MelSpectrogram.mlcomputeplan.json ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "1_ios16.reshape_shape_x": {
3
+ "dispatch": "CPU",
4
+ "supported": [
5
+ "CPU",
6
+ "ANE"
7
+ ],
8
+ "cost": 1.6712
9
+ },
10
+ "5_pad_pad_x_constant_val_mode": {
11
+ "dispatch": "CPU",
12
+ "supported": [
13
+ "CPU"
14
+ ],
15
+ "cost": 1.672
16
+ },
17
+ "7_ios16.reshape_shape_x": {
18
+ "dispatch": "CPU",
19
+ "supported": [
20
+ "CPU",
21
+ "ANE"
22
+ ],
23
+ "cost": 1.6726
24
+ },
25
+ "9_expand_dims_x_axes": {
26
+ "dispatch": "CPU",
27
+ "supported": [
28
+ "CPU",
29
+ "ANE"
30
+ ],
31
+ "cost": 1.6726
32
+ },
33
+ "12_expand_dims_x_axes": {
34
+ "dispatch": "CPU",
35
+ "supported": [
36
+ "CPU",
37
+ "ANE"
38
+ ],
39
+ "cost": 1.6726
40
+ },
41
+ "18_ios16.conv_groups_weight_x_dilations_strides_pad_pad_type": {
42
+ "dispatch": "CPU",
43
+ "supported": [
44
+ "CPU"
45
+ ],
46
+ "cost": 35.0484
47
+ },
48
+ "24_ios16.conv_groups_weight_x_dilations_strides_pad_pad_type": {
49
+ "dispatch": "CPU",
50
+ "supported": [
51
+ "CPU"
52
+ ],
53
+ "cost": 35.0484
54
+ },
55
+ "26_squeeze_x_axes": {
56
+ "dispatch": "ANE",
57
+ "supported": [
58
+ "CPU",
59
+ "ANE"
60
+ ],
61
+ "cost": 1.7502
62
+ },
63
+ "28_squeeze_x_axes": {
64
+ "dispatch": "ANE",
65
+ "supported": [
66
+ "CPU",
67
+ "ANE"
68
+ ],
69
+ "cost": 1.7502
70
+ },
71
+ "29_ios16.square_x": {
72
+ "dispatch": "ANE",
73
+ "supported": [
74
+ "CPU",
75
+ "ANE"
76
+ ],
77
+ "cost": 1.7502
78
+ },
79
+ "30_ios16.square_x": {
80
+ "dispatch": "ANE",
81
+ "supported": [
82
+ "CPU",
83
+ "ANE"
84
+ ],
85
+ "cost": 1.7502
86
+ },
87
+ "31_ios16.add_x_y": {
88
+ "dispatch": "ANE",
89
+ "supported": [
90
+ "CPU",
91
+ "ANE"
92
+ ],
93
+ "cost": 3.8783
94
+ },
95
+ "32_identity_x": {
96
+ "dispatch": "ANE",
97
+ "supported": [
98
+ "CPU",
99
+ "ANE"
100
+ ],
101
+ "cost": 1.7502
102
+ },
103
+ "36_slice_by_index_begin_end_end_mask_x": {
104
+ "dispatch": "ANE",
105
+ "supported": [
106
+ "CPU",
107
+ "ANE"
108
+ ],
109
+ "cost": 1.7499
110
+ },
111
+ "40_ios16.matmul_y_transpose_y_transpose_x_x": {
112
+ "dispatch": "ANE",
113
+ "supported": [
114
+ "CPU",
115
+ "ANE"
116
+ ],
117
+ "cost": 1.2463
118
+ },
119
+ "42_ios16.add_x_y": {
120
+ "dispatch": "ANE",
121
+ "supported": [
122
+ "CPU",
123
+ "ANE"
124
+ ],
125
+ "cost": 0.7715
126
+ },
127
+ "44_ios16.log_epsilon_x": {
128
+ "dispatch": "ANE",
129
+ "supported": [
130
+ "CPU",
131
+ "ANE"
132
+ ],
133
+ "cost": 0.6964
134
+ },
135
+ "46_ios16.mul_x_y": {
136
+ "dispatch": "ANE",
137
+ "supported": [
138
+ "CPU",
139
+ "ANE"
140
+ ],
141
+ "cost": 0.62
142
+ },
143
+ "48_ios16.reduce_max_x_keep_dims": {
144
+ "dispatch": "ANE",
145
+ "supported": [
146
+ "CPU",
147
+ "ANE"
148
+ ],
149
+ "cost": 0.3482
150
+ },
151
+ "50_ios16.sub_x_y": {
152
+ "dispatch": "ANE",
153
+ "supported": [
154
+ "CPU",
155
+ "ANE"
156
+ ],
157
+ "cost": 0.0
158
+ },
159
+ "51_ios16.maximum_x_y": {
160
+ "dispatch": "ANE",
161
+ "supported": [
162
+ "CPU",
163
+ "ANE"
164
+ ],
165
+ "cost": 0.6964
166
+ },
167
+ "53_ios16.add_x_y": {
168
+ "dispatch": "ANE",
169
+ "supported": [
170
+ "CPU",
171
+ "ANE"
172
+ ],
173
+ "cost": 0.7715
174
+ },
175
+ "55_ios16.mul_x_y": {
176
+ "dispatch": "ANE",
177
+ "supported": [
178
+ "CPU",
179
+ "ANE"
180
+ ],
181
+ "cost": 0.62
182
+ },
183
+ "57_expand_dims_x_axes": {
184
+ "dispatch": "ANE",
185
+ "supported": [
186
+ "CPU",
187
+ "ANE"
188
+ ],
189
+ "cost": 0.6964
190
+ },
191
+ "59_expand_dims_x_axes": {
192
+ "dispatch": "ANE",
193
+ "supported": [
194
+ "CPU",
195
+ "ANE"
196
+ ],
197
+ "cost": 0.6964
198
+ }
199
+ }
LocalDoc_azerbaijani-whisper-small/MelSpectrogram.mlmodelc/analytics/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c43685d3a81673e35d2daf64affb3f77c42a8a1cc642e2f3e1c5f52eee59935
3
+ size 243
LocalDoc_azerbaijani-whisper-small/MelSpectrogram.mlmodelc/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b023caf9e43b69c6ee43252c0d99b49ca7d5c6e8574fc3863eb8bf02a6d2c5f3
3
+ size 389
LocalDoc_azerbaijani-whisper-small/MelSpectrogram.mlmodelc/metadata.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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" : 7,
21
+ "mlProgramOperationTypeHistogram" : {
22
+ "Ios16.reshape" : 2,
23
+ "Ios16.mul" : 2,
24
+ "SliceByIndex" : 1,
25
+ "Ios16.sub" : 1,
26
+ "Ios16.log" : 1,
27
+ "Ios16.square" : 2,
28
+ "Ios16.add" : 3,
29
+ "Squeeze" : 2,
30
+ "Ios16.matmul" : 1,
31
+ "Ios16.conv" : 2,
32
+ "Ios16.maximum" : 1,
33
+ "ExpandDims" : 4,
34
+ "Ios16.reduceMax" : 1,
35
+ "Identity" : 1,
36
+ "Pad" : 1
37
+ },
38
+ "computePrecision" : "Mixed (Float16, Int32)",
39
+ "isUpdatable" : "0",
40
+ "stateSchema" : [
41
+
42
+ ],
43
+ "availability" : {
44
+ "macOS" : "13.0",
45
+ "tvOS" : "16.0",
46
+ "visionOS" : "1.0",
47
+ "watchOS" : "9.0",
48
+ "iOS" : "16.0",
49
+ "macCatalyst" : "16.0"
50
+ },
51
+ "modelType" : {
52
+ "name" : "MLModelType_mlProgram"
53
+ },
54
+ "userDefinedMetadata" : {
55
+ "com.github.apple.coremltools.conversion_date" : "2026-03-28",
56
+ "com.github.apple.coremltools.source" : "torch==2.2.2",
57
+ "com.github.apple.coremltools.version" : "9.0",
58
+ "com.github.apple.coremltools.source_dialect" : "TorchScript"
59
+ },
60
+ "inputSchema" : [
61
+ {
62
+ "hasShapeFlexibility" : "0",
63
+ "isOptional" : "0",
64
+ "dataType" : "Float16",
65
+ "formattedType" : "MultiArray (Float16 480000)",
66
+ "shortDescription" : "",
67
+ "shape" : "[480000]",
68
+ "name" : "audio",
69
+ "type" : "MultiArray"
70
+ }
71
+ ],
72
+ "generatedClassName" : "MelSpectrogram",
73
+ "method" : "predict"
74
+ }
75
+ ]
LocalDoc_azerbaijani-whisper-small/MelSpectrogram.mlmodelc/model.mil ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ program(1.0)
2
+ [buildInfo = dict<tensor<string, []>, tensor<string, []>>({{"coremlc-component-MIL", "3500.14.1"}, {"coremlc-version", "3500.32.1"}, {"coremltools-component-torch", "2.2.2"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "9.0"}})]
3
+ {
4
+ func main<ios16>(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]> input_1_cast_fp16 = reshape(shape = var_10, x = audio)[name = tensor<string, []>("input_1_cast_fp16")];
7
+ 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])];
8
+ tensor<string, []> input_3_mode_0 = const()[name = tensor<string, []>("input_3_mode_0"), val = tensor<string, []>("reflect")];
9
+ tensor<fp16, []> const_1_to_fp16 = const()[name = tensor<string, []>("const_1_to_fp16"), val = tensor<fp16, []>(0x0p+0)];
10
+ tensor<fp16, [1, 1, 480400]> input_3_cast_fp16 = pad(constant_val = const_1_to_fp16, mode = input_3_mode_0, pad = input_3_pad_0, x = input_1_cast_fp16)[name = tensor<string, []>("input_3_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_3_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<fp16, []> log_0_epsilon_0_to_fp16 = const()[name = tensor<string, []>("log_0_epsilon_0_to_fp16"), val = tensor<fp16, []>(0x0p+0)];
49
+ tensor<fp16, [80, 3000]> log_0_cast_fp16 = log(epsilon = log_0_epsilon_0_to_fp16, 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
+ }
LocalDoc_azerbaijani-whisper-small/MelSpectrogram.mlmodelc/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6eb778151a64f50945b0f31f1e524a9ce05fa951645d4be90610d56b0a1d2f2
3
+ size 354080
LocalDoc_azerbaijani-whisper-small/TextDecoder.mlcomputeplan.json ADDED
The diff for this file is too large to render. See raw diff
 
LocalDoc_azerbaijani-whisper-small/TextDecoder.mlmodelc/analytics/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ae5ac815912fb5d629f40ed1d7799c5c6b6ecdd019d7256b8f68e5e4f52e49
3
+ size 243
LocalDoc_azerbaijani-whisper-small/TextDecoder.mlmodelc/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7080a21ba2c423c2af7ba542be4d1aae0b0b3a2c196875bc0d76468af19724e
3
+ size 694
LocalDoc_azerbaijani-whisper-small/TextDecoder.mlmodelc/metadata.json ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 × 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 × 9216 × 1 × 1)",
21
+ "shortDescription" : "",
22
+ "shape" : "[1, 9216, 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 × 9216 × 1 × 1)",
31
+ "shortDescription" : "",
32
+ "shape" : "[1, 9216, 1, 1]",
33
+ "name" : "value_cache_updates",
34
+ "type" : "MultiArray"
35
+ },
36
+ {
37
+ "hasShapeFlexibility" : "0",
38
+ "isOptional" : "0",
39
+ "dataType" : "Float16",
40
+ "formattedType" : "MultiArray (Float16 1 × 1500)",
41
+ "shortDescription" : "",
42
+ "shape" : "[1, 1500]",
43
+ "name" : "alignment_heads_weights",
44
+ "type" : "MultiArray"
45
+ }
46
+ ],
47
+ "modelParameters" : [
48
+
49
+ ],
50
+ "specificationVersion" : 7,
51
+ "mlProgramOperationTypeHistogram" : {
52
+ "Ios16.linear" : 1,
53
+ "Concat" : 3,
54
+ "Ios16.reduceMean" : 1,
55
+ "Ios16.mul" : 72,
56
+ "Ios16.layerNorm" : 37,
57
+ "SliceByIndex" : 20,
58
+ "Ios16.sub" : 1,
59
+ "Transpose" : 1,
60
+ "Ios16.conv" : 120,
61
+ "Ios16.add" : 73,
62
+ "Squeeze" : 1,
63
+ "Ios16.matmul" : 48,
64
+ "Ios16.softmax" : 24,
65
+ "Ios16.gelu" : 12,
66
+ "ExpandDims" : 6,
67
+ "Ios16.batchNorm" : 37,
68
+ "Split" : 2,
69
+ "Ios16.gather" : 2,
70
+ "Ios16.reshape" : 96
71
+ },
72
+ "computePrecision" : "Mixed (Float16, Int32)",
73
+ "isUpdatable" : "0",
74
+ "stateSchema" : [
75
+
76
+ ],
77
+ "availability" : {
78
+ "macOS" : "13.0",
79
+ "tvOS" : "16.0",
80
+ "visionOS" : "1.0",
81
+ "watchOS" : "9.0",
82
+ "iOS" : "16.0",
83
+ "macCatalyst" : "16.0"
84
+ },
85
+ "modelType" : {
86
+ "name" : "MLModelType_mlProgram"
87
+ },
88
+ "userDefinedMetadata" : {
89
+ "com.github.apple.coremltools.conversion_date" : "2026-03-28",
90
+ "com.github.apple.coremltools.source" : "torch==2.2.2",
91
+ "com.github.apple.coremltools.version" : "9.0",
92
+ "com.github.apple.coremltools.source_dialect" : "TorchScript"
93
+ },
94
+ "inputSchema" : [
95
+ {
96
+ "hasShapeFlexibility" : "0",
97
+ "isOptional" : "0",
98
+ "dataType" : "Int32",
99
+ "formattedType" : "MultiArray (Int32 1)",
100
+ "shortDescription" : "",
101
+ "shape" : "[1]",
102
+ "name" : "input_ids",
103
+ "type" : "MultiArray"
104
+ },
105
+ {
106
+ "hasShapeFlexibility" : "0",
107
+ "isOptional" : "0",
108
+ "dataType" : "Int32",
109
+ "formattedType" : "MultiArray (Int32 1)",
110
+ "shortDescription" : "",
111
+ "shape" : "[1]",
112
+ "name" : "cache_length",
113
+ "type" : "MultiArray"
114
+ },
115
+ {
116
+ "hasShapeFlexibility" : "0",
117
+ "isOptional" : "0",
118
+ "dataType" : "Float16",
119
+ "formattedType" : "MultiArray (Float16 1 × 9216 × 1 × 448)",
120
+ "shortDescription" : "",
121
+ "shape" : "[1, 9216, 1, 448]",
122
+ "name" : "key_cache",
123
+ "type" : "MultiArray"
124
+ },
125
+ {
126
+ "hasShapeFlexibility" : "0",
127
+ "isOptional" : "0",
128
+ "dataType" : "Float16",
129
+ "formattedType" : "MultiArray (Float16 1 × 9216 × 1 × 448)",
130
+ "shortDescription" : "",
131
+ "shape" : "[1, 9216, 1, 448]",
132
+ "name" : "value_cache",
133
+ "type" : "MultiArray"
134
+ },
135
+ {
136
+ "hasShapeFlexibility" : "0",
137
+ "isOptional" : "0",
138
+ "dataType" : "Float16",
139
+ "formattedType" : "MultiArray (Float16 1 × 448)",
140
+ "shortDescription" : "",
141
+ "shape" : "[1, 448]",
142
+ "name" : "kv_cache_update_mask",
143
+ "type" : "MultiArray"
144
+ },
145
+ {
146
+ "hasShapeFlexibility" : "0",
147
+ "isOptional" : "0",
148
+ "dataType" : "Float16",
149
+ "formattedType" : "MultiArray (Float16 1 × 768 × 1 × 1500)",
150
+ "shortDescription" : "",
151
+ "shape" : "[1, 768, 1, 1500]",
152
+ "name" : "encoder_output_embeds",
153
+ "type" : "MultiArray"
154
+ },
155
+ {
156
+ "hasShapeFlexibility" : "0",
157
+ "isOptional" : "0",
158
+ "dataType" : "Float16",
159
+ "formattedType" : "MultiArray (Float16 1 × 448)",
160
+ "shortDescription" : "",
161
+ "shape" : "[1, 448]",
162
+ "name" : "decoder_key_padding_mask",
163
+ "type" : "MultiArray"
164
+ }
165
+ ],
166
+ "generatedClassName" : "TextDecoder",
167
+ "method" : "predict"
168
+ }
169
+ ]
LocalDoc_azerbaijani-whisper-small/TextDecoder.mlmodelc/model.mil ADDED
The diff for this file is too large to render. See raw diff
 
LocalDoc_azerbaijani-whisper-small/TextDecoder.mlmodelc/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:221f5743844b67cc82ea98cba8edf377b00ff7187fb5e5ebc1b7c30ae4576b2e
3
+ size 307287346
LocalDoc_azerbaijani-whisper-small/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 50257,
10
+ "classifier_proj_size": 256,
11
+ "d_model": 768,
12
+ "decoder_attention_heads": 12,
13
+ "decoder_ffn_dim": 3072,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 12,
16
+ "decoder_start_token_id": 50258,
17
+ "dropout": 0.0,
18
+ "dtype": "float32",
19
+ "encoder_attention_heads": 12,
20
+ "encoder_ffn_dim": 3072,
21
+ "encoder_layerdrop": 0.0,
22
+ "encoder_layers": 12,
23
+ "eos_token_id": 50257,
24
+ "forced_decoder_ids": [
25
+ [
26
+ 1,
27
+ 50259
28
+ ],
29
+ [
30
+ 2,
31
+ 50359
32
+ ],
33
+ [
34
+ 3,
35
+ 50363
36
+ ]
37
+ ],
38
+ "init_std": 0.02,
39
+ "is_encoder_decoder": true,
40
+ "mask_feature_length": 10,
41
+ "mask_feature_min_masks": 0,
42
+ "mask_feature_prob": 0.0,
43
+ "mask_time_length": 10,
44
+ "mask_time_min_masks": 2,
45
+ "mask_time_prob": 0.05,
46
+ "max_source_positions": 1500,
47
+ "max_target_positions": 448,
48
+ "median_filter_width": 7,
49
+ "model_type": "whisper",
50
+ "num_hidden_layers": 12,
51
+ "num_mel_bins": 80,
52
+ "pad_token_id": 50257,
53
+ "scale_embedding": false,
54
+ "tie_word_embeddings": true,
55
+ "transformers_version": "5.3.0",
56
+ "use_cache": true,
57
+ "use_weighted_layer_sum": false,
58
+ "vocab_size": 51865
59
+ }
LocalDoc_azerbaijani-whisper-small/coreml_manifest.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "LocalDoc/azerbaijani-whisper-small",
3
+ "architectures": [
4
+ "WhisperForConditionalGeneration"
5
+ ],
6
+ "num_mel_bins": 80,
7
+ "max_source_positions": 1500,
8
+ "max_target_positions": 448,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 50258,
11
+ "eos_token_id": 50257,
12
+ "pad_token_id": 50257,
13
+ "bos_token_id": 50257,
14
+ "max_decoder_length_exported": 128,
15
+ "sample_rate_hz": 16000,
16
+ "encoder_input_shape": [
17
+ 1,
18
+ 80,
19
+ 3000
20
+ ]
21
+ }
LocalDoc_azerbaijani-whisper-small/decoder_prompt_az_transcribe.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ [
3
+ 1,
4
+ 50304
5
+ ],
6
+ [
7
+ 2,
8
+ 50359
9
+ ],
10
+ [
11
+ 3,
12
+ 50363
13
+ ]
14
+ ]
LocalDoc_azerbaijani-whisper-small/generation_config.json ADDED
@@ -0,0 +1,264 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 5,
5
+ 3
6
+ ],
7
+ [
8
+ 5,
9
+ 9
10
+ ],
11
+ [
12
+ 8,
13
+ 0
14
+ ],
15
+ [
16
+ 8,
17
+ 4
18
+ ],
19
+ [
20
+ 8,
21
+ 7
22
+ ],
23
+ [
24
+ 8,
25
+ 8
26
+ ],
27
+ [
28
+ 9,
29
+ 0
30
+ ],
31
+ [
32
+ 9,
33
+ 7
34
+ ],
35
+ [
36
+ 9,
37
+ 9
38
+ ],
39
+ [
40
+ 10,
41
+ 5
42
+ ]
43
+ ],
44
+ "begin_suppress_tokens": [
45
+ 220,
46
+ 50257
47
+ ],
48
+ "bos_token_id": 50257,
49
+ "decoder_start_token_id": 50258,
50
+ "eos_token_id": 50257,
51
+ "forced_decoder_ids": [
52
+ [
53
+ 1,
54
+ null
55
+ ],
56
+ [
57
+ 2,
58
+ 50359
59
+ ]
60
+ ],
61
+ "is_multilingual": true,
62
+ "lang_to_id": {
63
+ "<|af|>": 50327,
64
+ "<|am|>": 50334,
65
+ "<|ar|>": 50272,
66
+ "<|as|>": 50350,
67
+ "<|az|>": 50304,
68
+ "<|ba|>": 50355,
69
+ "<|be|>": 50330,
70
+ "<|bg|>": 50292,
71
+ "<|bn|>": 50302,
72
+ "<|bo|>": 50347,
73
+ "<|br|>": 50309,
74
+ "<|bs|>": 50315,
75
+ "<|ca|>": 50270,
76
+ "<|cs|>": 50283,
77
+ "<|cy|>": 50297,
78
+ "<|da|>": 50285,
79
+ "<|de|>": 50261,
80
+ "<|el|>": 50281,
81
+ "<|en|>": 50259,
82
+ "<|es|>": 50262,
83
+ "<|et|>": 50307,
84
+ "<|eu|>": 50310,
85
+ "<|fa|>": 50300,
86
+ "<|fi|>": 50277,
87
+ "<|fo|>": 50338,
88
+ "<|fr|>": 50265,
89
+ "<|gl|>": 50319,
90
+ "<|gu|>": 50333,
91
+ "<|haw|>": 50352,
92
+ "<|ha|>": 50354,
93
+ "<|he|>": 50279,
94
+ "<|hi|>": 50276,
95
+ "<|hr|>": 50291,
96
+ "<|ht|>": 50339,
97
+ "<|hu|>": 50286,
98
+ "<|hy|>": 50312,
99
+ "<|id|>": 50275,
100
+ "<|is|>": 50311,
101
+ "<|it|>": 50274,
102
+ "<|ja|>": 50266,
103
+ "<|jw|>": 50356,
104
+ "<|ka|>": 50329,
105
+ "<|kk|>": 50316,
106
+ "<|km|>": 50323,
107
+ "<|kn|>": 50306,
108
+ "<|ko|>": 50264,
109
+ "<|la|>": 50294,
110
+ "<|lb|>": 50345,
111
+ "<|ln|>": 50353,
112
+ "<|lo|>": 50336,
113
+ "<|lt|>": 50293,
114
+ "<|lv|>": 50301,
115
+ "<|mg|>": 50349,
116
+ "<|mi|>": 50295,
117
+ "<|mk|>": 50308,
118
+ "<|ml|>": 50296,
119
+ "<|mn|>": 50314,
120
+ "<|mr|>": 50320,
121
+ "<|ms|>": 50282,
122
+ "<|mt|>": 50343,
123
+ "<|my|>": 50346,
124
+ "<|ne|>": 50313,
125
+ "<|nl|>": 50271,
126
+ "<|nn|>": 50342,
127
+ "<|no|>": 50288,
128
+ "<|oc|>": 50328,
129
+ "<|pa|>": 50321,
130
+ "<|pl|>": 50269,
131
+ "<|ps|>": 50340,
132
+ "<|pt|>": 50267,
133
+ "<|ro|>": 50284,
134
+ "<|ru|>": 50263,
135
+ "<|sa|>": 50344,
136
+ "<|sd|>": 50332,
137
+ "<|si|>": 50322,
138
+ "<|sk|>": 50298,
139
+ "<|sl|>": 50305,
140
+ "<|sn|>": 50324,
141
+ "<|so|>": 50326,
142
+ "<|sq|>": 50317,
143
+ "<|sr|>": 50303,
144
+ "<|su|>": 50357,
145
+ "<|sv|>": 50273,
146
+ "<|sw|>": 50318,
147
+ "<|ta|>": 50287,
148
+ "<|te|>": 50299,
149
+ "<|tg|>": 50331,
150
+ "<|th|>": 50289,
151
+ "<|tk|>": 50341,
152
+ "<|tl|>": 50348,
153
+ "<|tr|>": 50268,
154
+ "<|tt|>": 50351,
155
+ "<|uk|>": 50280,
156
+ "<|ur|>": 50290,
157
+ "<|uz|>": 50337,
158
+ "<|vi|>": 50278,
159
+ "<|yi|>": 50335,
160
+ "<|yo|>": 50325,
161
+ "<|zh|>": 50260
162
+ },
163
+ "max_initial_timestamp_index": 50,
164
+ "max_length": 448,
165
+ "no_timestamps_token_id": 50363,
166
+ "pad_token_id": 50257,
167
+ "prev_sot_token_id": 50361,
168
+ "return_timestamps": false,
169
+ "suppress_tokens": [
170
+ 1,
171
+ 2,
172
+ 7,
173
+ 8,
174
+ 9,
175
+ 10,
176
+ 14,
177
+ 25,
178
+ 26,
179
+ 27,
180
+ 28,
181
+ 29,
182
+ 31,
183
+ 58,
184
+ 59,
185
+ 60,
186
+ 61,
187
+ 62,
188
+ 63,
189
+ 90,
190
+ 91,
191
+ 92,
192
+ 93,
193
+ 359,
194
+ 503,
195
+ 522,
196
+ 542,
197
+ 873,
198
+ 893,
199
+ 902,
200
+ 918,
201
+ 922,
202
+ 931,
203
+ 1350,
204
+ 1853,
205
+ 1982,
206
+ 2460,
207
+ 2627,
208
+ 3246,
209
+ 3253,
210
+ 3268,
211
+ 3536,
212
+ 3846,
213
+ 3961,
214
+ 4183,
215
+ 4667,
216
+ 6585,
217
+ 6647,
218
+ 7273,
219
+ 9061,
220
+ 9383,
221
+ 10428,
222
+ 10929,
223
+ 11938,
224
+ 12033,
225
+ 12331,
226
+ 12562,
227
+ 13793,
228
+ 14157,
229
+ 14635,
230
+ 15265,
231
+ 15618,
232
+ 16553,
233
+ 16604,
234
+ 18362,
235
+ 18956,
236
+ 20075,
237
+ 21675,
238
+ 22520,
239
+ 26130,
240
+ 26161,
241
+ 26435,
242
+ 28279,
243
+ 29464,
244
+ 31650,
245
+ 32302,
246
+ 32470,
247
+ 36865,
248
+ 42863,
249
+ 47425,
250
+ 49870,
251
+ 50254,
252
+ 50258,
253
+ 50358,
254
+ 50359,
255
+ 50360,
256
+ 50361,
257
+ 50362
258
+ ],
259
+ "task_to_id": {
260
+ "transcribe": 50359,
261
+ "translate": 50358
262
+ },
263
+ "transformers_version": "5.3.0"
264
+ }
LocalDoc_azerbaijani-whisper-small/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
LocalDoc_azerbaijani-whisper-small/tokenizer_config.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "clean_up_tokenization_spaces": true,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|endoftext|>",
10
+ "<|startoftranscript|>",
11
+ "<|en|>",
12
+ "<|zh|>",
13
+ "<|de|>",
14
+ "<|es|>",
15
+ "<|ru|>",
16
+ "<|ko|>",
17
+ "<|fr|>",
18
+ "<|ja|>",
19
+ "<|pt|>",
20
+ "<|tr|>",
21
+ "<|pl|>",
22
+ "<|ca|>",
23
+ "<|nl|>",
24
+ "<|ar|>",
25
+ "<|sv|>",
26
+ "<|it|>",
27
+ "<|id|>",
28
+ "<|hi|>",
29
+ "<|fi|>",
30
+ "<|vi|>",
31
+ "<|he|>",
32
+ "<|uk|>",
33
+ "<|el|>",
34
+ "<|ms|>",
35
+ "<|cs|>",
36
+ "<|ro|>",
37
+ "<|da|>",
38
+ "<|hu|>",
39
+ "<|ta|>",
40
+ "<|no|>",
41
+ "<|th|>",
42
+ "<|ur|>",
43
+ "<|hr|>",
44
+ "<|bg|>",
45
+ "<|lt|>",
46
+ "<|la|>",
47
+ "<|mi|>",
48
+ "<|ml|>",
49
+ "<|cy|>",
50
+ "<|sk|>",
51
+ "<|te|>",
52
+ "<|fa|>",
53
+ "<|lv|>",
54
+ "<|bn|>",
55
+ "<|sr|>",
56
+ "<|az|>",
57
+ "<|sl|>",
58
+ "<|kn|>",
59
+ "<|et|>",
60
+ "<|mk|>",
61
+ "<|br|>",
62
+ "<|eu|>",
63
+ "<|is|>",
64
+ "<|hy|>",
65
+ "<|ne|>",
66
+ "<|mn|>",
67
+ "<|bs|>",
68
+ "<|kk|>",
69
+ "<|sq|>",
70
+ "<|sw|>",
71
+ "<|gl|>",
72
+ "<|mr|>",
73
+ "<|pa|>",
74
+ "<|si|>",
75
+ "<|km|>",
76
+ "<|sn|>",
77
+ "<|yo|>",
78
+ "<|so|>",
79
+ "<|af|>",
80
+ "<|oc|>",
81
+ "<|ka|>",
82
+ "<|be|>",
83
+ "<|tg|>",
84
+ "<|sd|>",
85
+ "<|gu|>",
86
+ "<|am|>",
87
+ "<|yi|>",
88
+ "<|lo|>",
89
+ "<|uz|>",
90
+ "<|fo|>",
91
+ "<|ht|>",
92
+ "<|ps|>",
93
+ "<|tk|>",
94
+ "<|nn|>",
95
+ "<|mt|>",
96
+ "<|sa|>",
97
+ "<|lb|>",
98
+ "<|my|>",
99
+ "<|bo|>",
100
+ "<|tl|>",
101
+ "<|mg|>",
102
+ "<|as|>",
103
+ "<|tt|>",
104
+ "<|haw|>",
105
+ "<|ln|>",
106
+ "<|ha|>",
107
+ "<|ba|>",
108
+ "<|jw|>",
109
+ "<|su|>",
110
+ "<|translate|>",
111
+ "<|transcribe|>",
112
+ "<|startoflm|>",
113
+ "<|startofprev|>",
114
+ "<|nocaptions|>",
115
+ "<|notimestamps|>"
116
+ ],
117
+ "is_local": false,
118
+ "language": null,
119
+ "model_max_length": 1024,
120
+ "pad_token": "<|endoftext|>",
121
+ "predict_timestamps": false,
122
+ "processor_class": "WhisperProcessor",
123
+ "return_attention_mask": false,
124
+ "task": null,
125
+ "tokenizer_class": "WhisperTokenizer",
126
+ "unk_token": "<|endoftext|>"
127
+ }