Training in progress, step 1500
Browse files- .gitignore +1 -0
- config.json +107 -0
- preprocessor_config.json +9 -0
- pytorch_model.bin +3 -0
- runs/Jan26_00-02-24_job-fa775f5b-8438-4c3d-95fa-ed70ddaee577/1643155382.524728/events.out.tfevents.1643155382.job-fa775f5b-8438-4c3d-95fa-ed70ddaee577.14643.1 +3 -0
- runs/Jan26_00-02-24_job-fa775f5b-8438-4c3d-95fa-ed70ddaee577/events.out.tfevents.1643155382.job-fa775f5b-8438-4c3d-95fa-ed70ddaee577.14643.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +1 -1
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-xls-r-300m",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"adapter_kernel_size": 3,
|
5 |
+
"adapter_stride": 2,
|
6 |
+
"add_adapter": false,
|
7 |
+
"apply_spec_augment": true,
|
8 |
+
"architectures": [
|
9 |
+
"Wav2Vec2ForCTC"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.2,
|
12 |
+
"bos_token_id": 1,
|
13 |
+
"classifier_proj_size": 256,
|
14 |
+
"codevector_dim": 768,
|
15 |
+
"contrastive_logits_temperature": 0.1,
|
16 |
+
"conv_bias": true,
|
17 |
+
"conv_dim": [
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512,
|
21 |
+
512,
|
22 |
+
512,
|
23 |
+
512,
|
24 |
+
512
|
25 |
+
],
|
26 |
+
"conv_kernel": [
|
27 |
+
10,
|
28 |
+
3,
|
29 |
+
3,
|
30 |
+
3,
|
31 |
+
3,
|
32 |
+
2,
|
33 |
+
2
|
34 |
+
],
|
35 |
+
"conv_stride": [
|
36 |
+
5,
|
37 |
+
2,
|
38 |
+
2,
|
39 |
+
2,
|
40 |
+
2,
|
41 |
+
2,
|
42 |
+
2
|
43 |
+
],
|
44 |
+
"ctc_loss_reduction": "mean",
|
45 |
+
"ctc_zero_infinity": false,
|
46 |
+
"diversity_loss_weight": 0.1,
|
47 |
+
"do_stable_layer_norm": true,
|
48 |
+
"eos_token_id": 2,
|
49 |
+
"feat_extract_activation": "gelu",
|
50 |
+
"feat_extract_dropout": 0.0,
|
51 |
+
"feat_extract_norm": "layer",
|
52 |
+
"feat_proj_dropout": 0.0,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.0,
|
55 |
+
"hidden_act": "gelu",
|
56 |
+
"hidden_dropout": 0.0,
|
57 |
+
"hidden_size": 1024,
|
58 |
+
"initializer_range": 0.02,
|
59 |
+
"intermediate_size": 4096,
|
60 |
+
"layer_norm_eps": 1e-05,
|
61 |
+
"layerdrop": 0.0,
|
62 |
+
"mask_feature_length": 64,
|
63 |
+
"mask_feature_min_masks": 0,
|
64 |
+
"mask_feature_prob": 0.25,
|
65 |
+
"mask_time_length": 10,
|
66 |
+
"mask_time_min_masks": 2,
|
67 |
+
"mask_time_prob": 0.15,
|
68 |
+
"model_type": "wav2vec2",
|
69 |
+
"num_adapter_layers": 3,
|
70 |
+
"num_attention_heads": 16,
|
71 |
+
"num_codevector_groups": 2,
|
72 |
+
"num_codevectors_per_group": 320,
|
73 |
+
"num_conv_pos_embedding_groups": 16,
|
74 |
+
"num_conv_pos_embeddings": 128,
|
75 |
+
"num_feat_extract_layers": 7,
|
76 |
+
"num_hidden_layers": 24,
|
77 |
+
"num_negatives": 100,
|
78 |
+
"output_hidden_size": 1024,
|
79 |
+
"pad_token_id": 0,
|
80 |
+
"proj_codevector_dim": 768,
|
81 |
+
"tdnn_dilation": [
|
82 |
+
1,
|
83 |
+
2,
|
84 |
+
3,
|
85 |
+
1,
|
86 |
+
1
|
87 |
+
],
|
88 |
+
"tdnn_dim": [
|
89 |
+
512,
|
90 |
+
512,
|
91 |
+
512,
|
92 |
+
512,
|
93 |
+
1500
|
94 |
+
],
|
95 |
+
"tdnn_kernel": [
|
96 |
+
5,
|
97 |
+
3,
|
98 |
+
3,
|
99 |
+
1,
|
100 |
+
1
|
101 |
+
],
|
102 |
+
"torch_dtype": "float32",
|
103 |
+
"transformers_version": "4.16.0.dev0",
|
104 |
+
"use_weighted_layer_sum": false,
|
105 |
+
"vocab_size": 696,
|
106 |
+
"xvector_output_dim": 512
|
107 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0,
|
7 |
+
"return_attention_mask": true,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b98f3b0c4cdbdb0e08433ea11233f1747b87e1d2393e4fa43967d95c773757a0
|
3 |
+
size 1264777329
|
runs/Jan26_00-02-24_job-fa775f5b-8438-4c3d-95fa-ed70ddaee577/1643155382.524728/events.out.tfevents.1643155382.job-fa775f5b-8438-4c3d-95fa-ed70ddaee577.14643.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bd3f70cf335dc40b28a0b71d42ccc0676d4f0daa9b0f8b6353c0e2ba03c99b2
|
3 |
+
size 4790
|
runs/Jan26_00-02-24_job-fa775f5b-8438-4c3d-95fa-ed70ddaee577/events.out.tfevents.1643155382.job-fa775f5b-8438-4c3d-95fa-ed70ddaee577.14643.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2304690facecfc52b81526d510d9b344e05319822d392838cfdf775330abc458
|
3 |
+
size 5196
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2WordpieceTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7e7866325381fdbf99b9d177296455c1a085c36f789bfeafd429ff192253377
|
3 |
+
size 3055
|
vocab.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{
|
|
|
1 |
+
{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "a": 5, "á": 6, "à": 7, "ả": 8, "ã": 9, "ạ": 10, "e": 11, "é": 12, "è": 13, "ẻ": 14, "ẽ": 15, "ẹ": 16, "ê": 17, "ế": 18, "ề": 19, "ể": 20, "ễ": 21, "ệ": 22, "i": 23, "í": 24, "ì": 25, "ỉ": 26, "ĩ": 27, "ị": 28, "o": 29, "ó": 30, "ò": 31, "ỏ": 32, "õ": 33, "ọ": 34, "ơ": 35, "ớ": 36, "ờ": 37, "ở": 38, "ỡ": 39, "ợ": 40, "ô": 41, "ố": 42, "ồ": 43, "ổ": 44, "ỗ": 45, "ộ": 46, "u": 47, "ú": 48, "ù": 49, "ủ": 50, "ũ": 51, "ụ": 52, "ư": 53, "ứ": 54, "ừ": 55, "ử": 56, "ữ": 57, "ự": 58, "y": 59, "ỳ": 60, "ý": 61, "ỷ": 62, "ỹ": 63, "ỵ": 64, "ă": 65, "ắ": 66, "ằ": 67, "ẳ": 68, "ẵ": 69, "ặ": 70, "â": 71, "ấ": 72, "ầ": 73, "ẩ": 74, "ẫ": 75, "ậ": 76, "đ": 77, "q": 78, "w": 79, "r": 80, "t": 81, "p": 82, "s": 83, "d": 84, "f": 85, "g": 86, "h": 87, "j": 88, "k": 89, "l": 90, "z": 91, "x": 92, "c": 93, "v": 94, "b": 95, "n": 96, "m": 97, "th": 98, "ch": 99, "kh": 100, "ph": 101, "nh": 102, "gh": 103, "qu": 104, "ng": 105, "ngh": 106, "tr": 107, "ác": 108, "ạc": 109, "ai": 110, "ái": 111, "ài": 112, "ải": 113, "ãi": 114, "ại": 115, "am": 116, "ám": 117, "àm": 118, "ảm": 119, "ãm": 120, "ạm": 121, "an": 122, "án": 123, "àn": 124, "ản": 125, "ãn": 126, "ạn": 127, "ao": 128, "áo": 129, "ào": 130, "ảo": 131, "ão": 132, "ạo": 133, "au": 134, "áu": 135, "àu": 136, "ảu": 137, "ãu": 138, "ạu": 139, "áp": 140, "ạp": 141, "át": 142, "ạt": 143, "ay": 144, "áy": 145, "ày": 146, "ảy": 147, "ãy": 148, "ạy": 149, "ắc": 150, "ặc": 151, "ăm": 152, "ằm": 153, "ắm": 154, "ẳm": 155, "ẵm": 156, "ặm": 157, "ăn": 158, "ắn": 159, "ằn": 160, "ẳn": 161, "ẵn": 162, "ặn": 163, "ắp": 164, "ặp": 165, "ắt": 166, "ặt": 167, "ấc": 168, "ậc": 169, "âm": 170, "ấm": 171, "ầm": 172, "ẩm": 173, "ẫm": 174, "ậm": 175, "ân": 176, "ấn": 177, "ần": 178, "ẩn": 179, "ẫn": 180, "ận": 181, "ấp": 182, "ập": 183, "ất": 184, "ật": 185, "âu": 186, "ấu": 187, "ầu": 188, "ẩu": 189, "ẫu": 190, "ậu": 191, "ây": 192, "ấy": 193, "ầy": 194, "ẩy": 195, "ẫy": 196, "ậy": 197, "éc": 198, "ẹc": 199, "em": 200, "ém": 201, "èm": 202, "ẻm": 203, "ẽm": 204, "ẹm": 205, "en": 206, "én": 207, "èn": 208, "ẻn": 209, "ẽn": 210, "ẹn": 211, "eo": 212, "éo": 213, "èo": 214, "ẻo": 215, "ẽo": 216, "ẹo": 217, "ép": 218, "ẹp": 219, "ét": 220, "ẹt": 221, "êm": 222, "ếm": 223, "ềm": 224, "ễm": 225, "ệm": 226, "ên": 227, "ến": 228, "ền": 229, "ển": 230, "ện": 231, "ếp": 232, "ệp": 233, "ết": 234, "ệt": 235, "êu": 236, "ếu": 237, "ều": 238, "ểu": 239, "ễu": 240, "ệu": 241, "ia": 242, "ía": 243, "ìa": 244, "ỉa": 245, "ĩa": 246, "ịa": 247, "im": 248, "ím": 249, "ìm": 250, "ỉm": 251, "ĩm": 252, "ịm": 253, "in": 254, "ín": 255, "ìn": 256, "ỉn": 257, "ịn": 258, "íp": 259, "ịp": 260, "ít": 261, "ịt": 262, "iu": 263, "íu": 264, "ìu": 265, "ỉu": 266, "ĩu": 267, "ịu": 268, "oa": 269, "óa": 270, "òa": 271, "ỏa": 272, "õa": 273, "ọa": 274, "oà": 275, "óc": 276, "ọc": 277, "oe": 278, "óe": 279, "òe": 280, "ỏe": 281, "ọe": 282, "oẹ": 283, "oi": 284, "ói": 285, "òi": 286, "ỏi": 287, "õi": 288, "ọi": 289, "om": 290, "óm": 291, "òm": 292, "ỏm": 293, "õm": 294, "ọm": 295, "on": 296, "ón": 297, "òn": 298, "ỏn": 299, "õn": 300, "ọn": 301, "óp": 302, "ọp": 303, "ót": 304, "ọt": 305, "ốc": 306, "ộc": 307, "ôi": 308, "ối": 309, "ồi": 310, "ổi": 311, "ỗi": 312, "ội": 313, "ôm": 314, "ốm": 315, "ồm": 316, "ổm": 317, "ỗm": 318, "ộm": 319, "ôn": 320, "ốn": 321, "ồn": 322, "ổn": 323, "ỗn": 324, "ộn": 325, "ốp": 326, "ộp": 327, "ốt": 328, "ột": 329, "ơi": 330, "ới": 331, "ời": 332, "ởi": 333, "ỡi": 334, "ợi": 335, "ơm": 336, "ớm": 337, "ờm": 338, "ởm": 339, "ỡm": 340, "ợm": 341, "ơn": 342, "ớn": 343, "ờn": 344, "ởn": 345, "ỡn": 346, "ợn": 347, "ớp": 348, "ợp": 349, "ớt": 350, "ợt": 351, "ua": 352, "úa": 353, "ùa": 354, "ủa": 355, "ũa": 356, "ụa": 357, "úc": 358, "ục": 359, "uê": 360, "uế": 361, "uề": 362, "uể": 363, "uệ": 364, "ui": 365, "úi": 366, "ùi": 367, "ủi": 368, "ũi": 369, "ụi": 370, "um": 371, "úm": 372, "ùm": 373, "ủm": 374, "ũm": 375, "ụm": 376, "un": 377, "ún": 378, "ùn": 379, "ủn": 380, "ũn": 381, "ụn": 382, "úp": 383, "ụp": 384, "út": 385, "ụt": 386, "uy": 387, "úy": 388, "ùy": 389, "ủy": 390, "ũy": 391, "ụy": 392, "ưa": 393, "ứa": 394, "ừa": 395, "ửa": 396, "ữa": 397, "ựa": 398, "ức": 399, "ực": 400, "ửi": 401, "ừm": 402, "uơ": 403, "uở": 404, "ứt": 405, "ựt": 406, "ưu": 407, "ứu": 408, "ừu": 409, "ửu": 410, "ữu": 411, "ựu": 412, "sh": 413, "aw": 414, "ee": 415, "ea": 416, "ei": 417, "ew": 418, "eu": 419, "ie": 420, "oo": 421, "ou": 422, "ow": 423, "oy": 424, "ue": 425, "io": 426, "ách": 427, "ạch": 428, "ang": 429, "áng": 430, "àng": 431, "ảng": 432, "ãng": 433, "ạng": 434, "anh": 435, "ánh": 436, "ành": 437, "ảnh": 438, "ãnh": 439, "ạnh": 440, "ăng": 441, "ắng": 442, "ằng": 443, "ẳng": 444, "ẵng": 445, "ặng": 446, "âng": 447, "ấng": 448, "ầng": 449, "ẩng": 450, "ẫng": 451, "ậng": 452, "eng": 453, "éng": 454, "èng": 455, "ẻng": 456, "ếch": 457, "ệch": 458, "ênh": 459, "ếnh": 460, "ềnh": 461, "ểnh": 462, "ễnh": 463, "ệnh": 464, "ích": 465, "ịch": 466, "iếc": 467, "iệc": 468, "iêm": 469, "iếm": 470, "iềm": 471, "iểm": 472, "iễm": 473, "iệm": 474, "iên": 475, "iến": 476, "iền": 477, "iển": 478, "iễn": 479, "iện": 480, "iếp": 481, "iệp": 482, "iết": 483, "iệt": 484, "iêu": 485, "iếu": 486, "iều": 487, "iểu": 488, "iễu": 489, "iệu": 490, "inh": 491, "ính": 492, "ình": 493, "ỉnh": 494, "ĩnh": 495, "ịnh": 496, "oác": 497, "oạc": 498, "oai": 499, "oái": 500, "oài": 501, "oải": 502, "oãi": 503, "oại": 504, "oàm": 505, "oan": 506, "oán": 507, "oàn": 508, "oản": 509, "oãn": 510, "oạn": 511, "oao": 512, "oáo": 513, "oáp": 514, "oạp": 515, "oát": 516, "oạt": 517, "oay": 518, "oáy": 519, "oảy": 520, "oắc": 521, "oặc": 522, "oăm": 523, "oăn": 524, "oẳn": 525, "oắn": 526, "oằn": 527, "oắt": 528, "oặt": 529, "oen": 530, "oẻn": 531, "oeo": 532, "oéo": 533, "oèo": 534, "oẻo": 535, "oét": 536, "oẹt": 537, "ong": 538, "óng": 539, "òng": 540, "ỏng": 541, "õng": 542, "ọng": 543, "oóc": 544, "oọc": 545, "ông": 546, "ống": 547, "ồng": 548, "ổng": 549, "ỗng": 550, "ộng": 551, "uân": 552, "uấn": 553, "uần": 554, "uẩn": 555, "uẫn": 556, "uận": 557, "uất": 558, "uật": 559, "uây": 560, "uấy": 561, "uầy": 562, "ung": 563, "úng": 564, "ùng": 565, "ủng": 566, "ũng": 567, "ụng": 568, "uốc": 569, "uộc": 570, "uôi": 571, "uối": 572, "uồi": 573, "uổi": 574, "uỗi": 575, "uội": 576, "uôm": 577, "uốm": 578, "uồm": 579, "uỗm": 580, "uộm": 581, "uôn": 582, "uốn": 583, "uồn": 584, "uỗn": 585, "uộn": 586, "uốt": 587, "uột": 588, "uýt": 589, "uỵt": 590, "uya": 591, "uỷu": 592, "ưng": 593, "ứng": 594, "ừng": 595, "ửng": 596, "ững": 597, "ựng": 598, "ước": 599, "ược": 600, "ươi": 601, "ưới": 602, "ười": 603, "ưởi": 604, "ưỡi": 605, "ượi": 606, "ươm": 607, "ướm": 608, "ườm": 609, "ượm": 610, "ươn": 611, "ướn": 612, "ườn": 613, "ưỡn": 614, "ượn": 615, "ướp": 616, "ượp": 617, "ướt": 618, "ượt": 619, "ươu": 620, "ướu": 621, "ượu": 622, "yêm": 623, "yếm": 624, "yểm": 625, "yên": 626, "yến": 627, "yêu": 628, "yếu": 629, "yểu": 630, "yết": 631, "iêng": 632, "iếng": 633, "iềng": 634, "iểng": 635, "iễng": 636, "iệng": 637, "oách": 638, "oạch": 639, "oang": 640, "oáng": 641, "oàng": 642, "oảng": 643, "oãng": 644, "oạng": 645, "oanh": 646, "oánh": 647, "oành": 648, "oạnh": 649, "oảnh": 650, "oăng": 651, "oắng": 652, "oằng": 653, "oẳng": 654, "oong": 655, "uếch": 656, "uênh": 657, "uông": 658, "uống": 659, "uồng": 660, "uổng": 661, "uỗng": 662, "uộng": 663, "uých": 664, "uỵch": 665, "uyên": 666, "uyến": 667, "uyền": 668, "uyển": 669, "uyễn": 670, "uyện": 671, "uyết": 672, "uyệt": 673, "uynh": 674, "uỳnh": 675, "uýnh": 676, "uỷnh": 677, "ương": 678, "ướng": 679, "ường": 680, "ưởng": 681, "ưỡng": 682, "ượng": 683, "op": 684, "ot": 685, "gi": 686, "ap": 687, "at": 688, "ac": 689, "it": 690, "ip": 691, "ic": 692, "ep": 693, "et": 694, "ec": 695}
|