Faris-ML commited on
Commit
774d9b2
·
verified ·
1 Parent(s): 5756014

Upload WhisperForConditionalGeneration

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/content/drive/MyDrive/Whatsapp bot/whisper-large-ar_2/checkpoint-10000",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
@@ -7,10 +7,7 @@
7
  "WhisperForConditionalGeneration"
8
  ],
9
  "attention_dropout": 0.0,
10
- "begin_suppress_tokens": [
11
- 220,
12
- 50257
13
- ],
14
  "bos_token_id": 50257,
15
  "classifier_proj_size": 256,
16
  "d_model": 1280,
@@ -25,20 +22,6 @@
25
  "encoder_layerdrop": 0.0,
26
  "encoder_layers": 32,
27
  "eos_token_id": 50257,
28
- "forced_decoder_ids": [
29
- [
30
- 1,
31
- 50259
32
- ],
33
- [
34
- 2,
35
- 50359
36
- ],
37
- [
38
- 3,
39
- 50363
40
- ]
41
- ],
42
  "init_std": 0.02,
43
  "is_encoder_decoder": true,
44
  "mask_feature_length": 10,
@@ -47,108 +30,18 @@
47
  "mask_time_length": 10,
48
  "mask_time_min_masks": 2,
49
  "mask_time_prob": 0.05,
50
- "max_length": 448,
51
  "max_source_positions": 1500,
52
  "max_target_positions": 448,
53
  "median_filter_width": 7,
54
  "model_type": "whisper",
55
  "num_hidden_layers": 32,
56
- "num_mel_bins": 80,
57
- "pad_token_id": 50257,
58
  "scale_embedding": false,
59
- "suppress_tokens": [
60
- 1,
61
- 2,
62
- 7,
63
- 8,
64
- 9,
65
- 10,
66
- 14,
67
- 25,
68
- 26,
69
- 27,
70
- 28,
71
- 29,
72
- 31,
73
- 58,
74
- 59,
75
- 60,
76
- 61,
77
- 62,
78
- 63,
79
- 90,
80
- 91,
81
- 92,
82
- 93,
83
- 359,
84
- 503,
85
- 522,
86
- 542,
87
- 873,
88
- 893,
89
- 902,
90
- 918,
91
- 922,
92
- 931,
93
- 1350,
94
- 1853,
95
- 1982,
96
- 2460,
97
- 2627,
98
- 3246,
99
- 3253,
100
- 3268,
101
- 3536,
102
- 3846,
103
- 3961,
104
- 4183,
105
- 4667,
106
- 6585,
107
- 6647,
108
- 7273,
109
- 9061,
110
- 9383,
111
- 10428,
112
- 10929,
113
- 11938,
114
- 12033,
115
- 12331,
116
- 12562,
117
- 13793,
118
- 14157,
119
- 14635,
120
- 15265,
121
- 15618,
122
- 16553,
123
- 16604,
124
- 18362,
125
- 18956,
126
- 20075,
127
- 21675,
128
- 22520,
129
- 26130,
130
- 26161,
131
- 26435,
132
- 28279,
133
- 29464,
134
- 31650,
135
- 32302,
136
- 32470,
137
- 36865,
138
- 42863,
139
- 47425,
140
- 49870,
141
- 50254,
142
- 50258,
143
- 50358,
144
- 50359,
145
- 50360,
146
- 50361,
147
- 50362
148
- ],
149
  "torch_dtype": "float32",
150
- "transformers_version": "4.42.3",
151
  "use_cache": true,
152
  "use_weighted_layer_sum": false,
153
- "vocab_size": 51865
154
  }
 
1
  {
2
+ "_name_or_path": "/content/drive/MyDrive/Whatsapp bot/whisper-large-v3-ar_v1/checkpoint-12000",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
 
7
  "WhisperForConditionalGeneration"
8
  ],
9
  "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": null,
 
 
 
11
  "bos_token_id": 50257,
12
  "classifier_proj_size": 256,
13
  "d_model": 1280,
 
22
  "encoder_layerdrop": 0.0,
23
  "encoder_layers": 32,
24
  "eos_token_id": 50257,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  "init_std": 0.02,
26
  "is_encoder_decoder": true,
27
  "mask_feature_length": 10,
 
30
  "mask_time_length": 10,
31
  "mask_time_min_masks": 2,
32
  "mask_time_prob": 0.05,
33
+ "max_length": null,
34
  "max_source_positions": 1500,
35
  "max_target_positions": 448,
36
  "median_filter_width": 7,
37
  "model_type": "whisper",
38
  "num_hidden_layers": 32,
39
+ "num_mel_bins": 128,
40
+ "pad_token_id": 50256,
41
  "scale_embedding": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  "torch_dtype": "float32",
43
+ "transformers_version": "4.45.2",
44
  "use_cache": true,
45
  "use_weighted_layer_sum": false,
46
+ "vocab_size": 51866
47
  }
generation_config.json CHANGED
@@ -1,40 +1,44 @@
1
  {
2
  "alignment_heads": [
3
  [
4
- 9,
5
- 19
6
  ],
7
  [
8
- 11,
9
- 2
10
  ],
11
  [
12
- 11,
13
- 4
14
  ],
15
  [
16
- 11,
17
- 17
18
  ],
19
  [
20
- 22,
21
- 7
22
  ],
23
  [
24
- 22,
 
 
 
 
25
  11
26
  ],
27
  [
28
- 22,
29
- 17
30
  ],
31
  [
32
- 23,
33
- 2
34
  ],
35
  [
36
- 23,
37
- 15
38
  ]
39
  ],
40
  "begin_suppress_tokens": [
@@ -44,6 +48,16 @@
44
  "bos_token_id": 50257,
45
  "decoder_start_token_id": 50258,
46
  "eos_token_id": 50257,
 
 
 
 
 
 
 
 
 
 
47
  "is_multilingual": true,
48
  "lang_to_id": {
49
  "<|af|>": 50327,
@@ -144,14 +158,15 @@
144
  "<|vi|>": 50278,
145
  "<|yi|>": 50335,
146
  "<|yo|>": 50325,
 
147
  "<|zh|>": 50260
148
  },
149
  "language": "arabic",
150
  "max_initial_timestamp_index": 50,
151
  "max_length": 448,
152
- "no_timestamps_token_id": 50363,
153
  "pad_token_id": 50257,
154
- "prev_sot_token_id": 50361,
155
  "return_timestamps": false,
156
  "suppress_tokens": [
157
  1,
@@ -237,16 +252,16 @@
237
  49870,
238
  50254,
239
  50258,
240
- 50358,
241
  50359,
242
  50360,
243
  50361,
244
- 50362
 
245
  ],
246
  "task": "transcribe",
247
  "task_to_id": {
248
- "transcribe": 50359,
249
- "translate": 50358
250
  },
251
- "transformers_version": "4.42.3"
252
  }
 
1
  {
2
  "alignment_heads": [
3
  [
4
+ 7,
5
+ 0
6
  ],
7
  [
8
+ 10,
9
+ 17
10
  ],
11
  [
12
+ 12,
13
+ 18
14
  ],
15
  [
16
+ 13,
17
+ 12
18
  ],
19
  [
20
+ 16,
21
+ 1
22
  ],
23
  [
24
+ 17,
25
+ 14
26
+ ],
27
+ [
28
+ 19,
29
  11
30
  ],
31
  [
32
+ 21,
33
+ 4
34
  ],
35
  [
36
+ 24,
37
+ 1
38
  ],
39
  [
40
+ 25,
41
+ 6
42
  ]
43
  ],
44
  "begin_suppress_tokens": [
 
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
+ 50360
59
+ ]
60
+ ],
61
  "is_multilingual": true,
62
  "lang_to_id": {
63
  "<|af|>": 50327,
 
158
  "<|vi|>": 50278,
159
  "<|yi|>": 50335,
160
  "<|yo|>": 50325,
161
+ "<|yue|>": 50358,
162
  "<|zh|>": 50260
163
  },
164
  "language": "arabic",
165
  "max_initial_timestamp_index": 50,
166
  "max_length": 448,
167
+ "no_timestamps_token_id": 50364,
168
  "pad_token_id": 50257,
169
+ "prev_sot_token_id": 50362,
170
  "return_timestamps": false,
171
  "suppress_tokens": [
172
  1,
 
252
  49870,
253
  50254,
254
  50258,
 
255
  50359,
256
  50360,
257
  50361,
258
+ 50362,
259
+ 50363
260
  ],
261
  "task": "transcribe",
262
  "task_to_id": {
263
+ "transcribe": 50360,
264
+ "translate": 50359
265
  },
266
+ "transformers_version": "4.45.2"
267
  }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:524b0fb1f18aa4eb40d966cbf547cd439a9e1ba9afb9d124649fb6506dd67045
3
- size 4992706480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4af896bf8c5967fd391e3f8dcb515b99dd736234f72d75ae78e117b60e28706
3
+ size 4993448880
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25b7d399fbdd6deb7ac6757d1a7f9d67ab8a16f62ad0c2544c99e9aa4688d4ec
3
  size 1180663192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1be95dc538d400ab4ad55908cb52cf25056074d595c26c7e360124b9cae85eac
3
  size 1180663192
model.safetensors.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 6173219840
4
  },
5
  "weight_map": {
6
  "model.decoder.embed_positions.weight": "model-00001-of-00002.safetensors",
 
1
  {
2
  "metadata": {
3
+ "total_size": 6173962240
4
  },
5
  "weight_map": {
6
  "model.decoder.embed_positions.weight": "model-00001-of-00002.safetensors",