eeasset-model 1.0.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,24 @@
1
+ """Rebuilds the Whisper large-v3-turbo (CTranslate2) model folder from the chunk packages."""
2
+ import hashlib, importlib, json, os, shutil
3
+ HERE = os.path.dirname(os.path.abspath(__file__))
4
+
5
+ def assemble(dest):
6
+ m = json.load(open(os.path.join(HERE, "manifest.json")))
7
+ os.makedirs(dest, exist_ok=True)
8
+ for f in m["files"]:
9
+ shutil.copy(os.path.join(HERE, f), os.path.join(dest, f))
10
+ h = hashlib.sha256()
11
+ out = os.path.join(dest, "model.bin")
12
+ with open(out + ".part", "wb") as w:
13
+ for p in m["parts"]:
14
+ src = os.path.join(os.path.dirname(importlib.import_module(p["pkg"]).__file__), "data.bin")
15
+ with open(src, "rb") as r:
16
+ while True:
17
+ b = r.read(1 << 24)
18
+ if not b:
19
+ break
20
+ h.update(b); w.write(b)
21
+ if h.hexdigest() != m["model_bin_sha256"]:
22
+ os.remove(out + ".part"); raise RuntimeError("model checksum mismatch")
23
+ os.replace(out + ".part", out)
24
+ return dest
@@ -0,0 +1,224 @@
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 2,
5
+ 4
6
+ ],
7
+ [
8
+ 2,
9
+ 11
10
+ ],
11
+ [
12
+ 3,
13
+ 3
14
+ ],
15
+ [
16
+ 3,
17
+ 6
18
+ ],
19
+ [
20
+ 3,
21
+ 11
22
+ ],
23
+ [
24
+ 3,
25
+ 14
26
+ ]
27
+ ],
28
+ "lang_ids": [
29
+ 50259,
30
+ 50260,
31
+ 50261,
32
+ 50262,
33
+ 50263,
34
+ 50264,
35
+ 50265,
36
+ 50266,
37
+ 50267,
38
+ 50268,
39
+ 50269,
40
+ 50270,
41
+ 50271,
42
+ 50272,
43
+ 50273,
44
+ 50274,
45
+ 50275,
46
+ 50276,
47
+ 50277,
48
+ 50278,
49
+ 50279,
50
+ 50280,
51
+ 50281,
52
+ 50282,
53
+ 50283,
54
+ 50284,
55
+ 50285,
56
+ 50286,
57
+ 50287,
58
+ 50288,
59
+ 50289,
60
+ 50290,
61
+ 50291,
62
+ 50292,
63
+ 50293,
64
+ 50294,
65
+ 50295,
66
+ 50296,
67
+ 50297,
68
+ 50298,
69
+ 50299,
70
+ 50300,
71
+ 50301,
72
+ 50302,
73
+ 50303,
74
+ 50304,
75
+ 50305,
76
+ 50306,
77
+ 50307,
78
+ 50308,
79
+ 50309,
80
+ 50310,
81
+ 50311,
82
+ 50312,
83
+ 50313,
84
+ 50314,
85
+ 50315,
86
+ 50316,
87
+ 50317,
88
+ 50318,
89
+ 50319,
90
+ 50320,
91
+ 50321,
92
+ 50322,
93
+ 50323,
94
+ 50324,
95
+ 50325,
96
+ 50326,
97
+ 50327,
98
+ 50328,
99
+ 50329,
100
+ 50330,
101
+ 50331,
102
+ 50332,
103
+ 50333,
104
+ 50334,
105
+ 50335,
106
+ 50336,
107
+ 50337,
108
+ 50338,
109
+ 50339,
110
+ 50340,
111
+ 50341,
112
+ 50342,
113
+ 50343,
114
+ 50344,
115
+ 50345,
116
+ 50346,
117
+ 50347,
118
+ 50348,
119
+ 50349,
120
+ 50350,
121
+ 50351,
122
+ 50352,
123
+ 50353,
124
+ 50354,
125
+ 50355,
126
+ 50356,
127
+ 50357,
128
+ 50358
129
+ ],
130
+ "suppress_ids": [
131
+ 1,
132
+ 2,
133
+ 7,
134
+ 8,
135
+ 9,
136
+ 10,
137
+ 14,
138
+ 25,
139
+ 26,
140
+ 27,
141
+ 28,
142
+ 29,
143
+ 31,
144
+ 58,
145
+ 59,
146
+ 60,
147
+ 61,
148
+ 62,
149
+ 63,
150
+ 90,
151
+ 91,
152
+ 92,
153
+ 93,
154
+ 359,
155
+ 503,
156
+ 522,
157
+ 542,
158
+ 873,
159
+ 893,
160
+ 902,
161
+ 918,
162
+ 922,
163
+ 931,
164
+ 1350,
165
+ 1853,
166
+ 1982,
167
+ 2460,
168
+ 2627,
169
+ 3246,
170
+ 3253,
171
+ 3268,
172
+ 3536,
173
+ 3846,
174
+ 3961,
175
+ 4183,
176
+ 4667,
177
+ 6585,
178
+ 6647,
179
+ 7273,
180
+ 9061,
181
+ 9383,
182
+ 10428,
183
+ 10929,
184
+ 11938,
185
+ 12033,
186
+ 12331,
187
+ 12562,
188
+ 13793,
189
+ 14157,
190
+ 14635,
191
+ 15265,
192
+ 15618,
193
+ 16553,
194
+ 16604,
195
+ 18362,
196
+ 18956,
197
+ 20075,
198
+ 21675,
199
+ 22520,
200
+ 26130,
201
+ 26161,
202
+ 26435,
203
+ 28279,
204
+ 29464,
205
+ 31650,
206
+ 32302,
207
+ 32470,
208
+ 36865,
209
+ 42863,
210
+ 47425,
211
+ 49870,
212
+ 50254,
213
+ 50258,
214
+ 50359,
215
+ 50360,
216
+ 50361,
217
+ 50362,
218
+ 50363
219
+ ],
220
+ "suppress_ids_begin": [
221
+ 220,
222
+ 50257
223
+ ]
224
+ }
@@ -0,0 +1,97 @@
1
+ {
2
+ "model_bin_sha256": "e76620f83d5f5b69efd3d87e3dc180c1bd21df9fbebacfd4335e5e1efcc018da",
3
+ "model_bin_bytes": 1617884929,
4
+ "parts": [
5
+ {
6
+ "pkg": "eeasset_model_01",
7
+ "sha256": "21068f75fde18556508ca83eb298ef0e88db6b48936bd8ddbb3bbf471cb98f82",
8
+ "bytes": 98000000
9
+ },
10
+ {
11
+ "pkg": "eeasset_model_02",
12
+ "sha256": "90fc1bf06f415adb29826cb04f27145bdc2140e0a1e0764d55518e544898752e",
13
+ "bytes": 98000000
14
+ },
15
+ {
16
+ "pkg": "eeasset_model_03",
17
+ "sha256": "5204f04f066d9123f9a4bc9f57a333faa45fa079d6a93ddeede71557696fd9b2",
18
+ "bytes": 98000000
19
+ },
20
+ {
21
+ "pkg": "eeasset_model_04",
22
+ "sha256": "26f4714c0e496cbbfa1e8ddd409e29c47ac218c52a843f6c4fd87188ff0e471f",
23
+ "bytes": 98000000
24
+ },
25
+ {
26
+ "pkg": "eeasset_model_05",
27
+ "sha256": "9a0f19e1828a91858078cb9cf3ce5e228d13b9f63d2efee7cd3e83d7fc86c884",
28
+ "bytes": 98000000
29
+ },
30
+ {
31
+ "pkg": "eeasset_model_06",
32
+ "sha256": "dd81d99326a8793c4fd0fe94b69c81dd762081063a50e430f62deed8b45a3f78",
33
+ "bytes": 98000000
34
+ },
35
+ {
36
+ "pkg": "eeasset_model_07",
37
+ "sha256": "1b6aec9771f9b67bf86f963174f934708581f2e1bc96918619798c0493566037",
38
+ "bytes": 98000000
39
+ },
40
+ {
41
+ "pkg": "eeasset_model_08",
42
+ "sha256": "b4db613c632c962b24c41f71a3d255c0a1c2d967f779e730d2c435e84336921f",
43
+ "bytes": 98000000
44
+ },
45
+ {
46
+ "pkg": "eeasset_model_09",
47
+ "sha256": "c604ab3181a68e30489ce1ddb03b6481f0f631fac296f35ac838acdbbec624e3",
48
+ "bytes": 98000000
49
+ },
50
+ {
51
+ "pkg": "eeasset_model_10",
52
+ "sha256": "1788fe1e80d146863c80538e7f2d7e5b47c5613b60b78976bf8b125c90b3bd56",
53
+ "bytes": 98000000
54
+ },
55
+ {
56
+ "pkg": "eeasset_model_11",
57
+ "sha256": "42afef5710832d56bdc64fd42aed529572077b5446d45723815f022a9f285ec4",
58
+ "bytes": 98000000
59
+ },
60
+ {
61
+ "pkg": "eeasset_model_12",
62
+ "sha256": "a6a033144ea9ad568352c6957deaa550bb8e03746aa8cb349170ccfe44466049",
63
+ "bytes": 98000000
64
+ },
65
+ {
66
+ "pkg": "eeasset_model_13",
67
+ "sha256": "f3cc741ab0405fc327b76a3ab7caf9190278486fea27521204eaaf8de6d6c913",
68
+ "bytes": 98000000
69
+ },
70
+ {
71
+ "pkg": "eeasset_model_14",
72
+ "sha256": "f5742bb0ec28799a9e837ca65ed083c456e1a7501ae8c18b5aaa9b07bbf0cd1c",
73
+ "bytes": 98000000
74
+ },
75
+ {
76
+ "pkg": "eeasset_model_15",
77
+ "sha256": "2c8e295d5aae46f1265d4bf34cf99f0d7b36e52d3c60dd46c31328901788c4bd",
78
+ "bytes": 98000000
79
+ },
80
+ {
81
+ "pkg": "eeasset_model_16",
82
+ "sha256": "d7bf6186172065fcb5230406fa4a7bd14e4f6a8936a26f3b305fa512c44f8326",
83
+ "bytes": 98000000
84
+ },
85
+ {
86
+ "pkg": "eeasset_model_17",
87
+ "sha256": "f5136d1ccd4aa35c85297c916ac7758032c721485a73f647d44a9021c812a04d",
88
+ "bytes": 49884929
89
+ }
90
+ ],
91
+ "files": [
92
+ "config.json",
93
+ "tokenizer.json",
94
+ "vocabulary.json",
95
+ "preprocessor_config.json"
96
+ ]
97
+ }
@@ -0,0 +1,14 @@
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 128,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
+ "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "WhisperProcessor",
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }