Yasinjan99
commited on
Commit
•
5245071
1
Parent(s):
577d49b
Training in progress, step 500
Browse files- added_tokens.json +4 -0
- config.json +109 -0
- model.safetensors +3 -0
- preprocessor_config.json +9 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +47 -0
- training_args.bin +3 -0
- vocab.json +41 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 40,
|
3 |
+
"<s>": 39
|
4 |
+
}
|
config.json
ADDED
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-xls-r-300m",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"adapter_attn_dim": null,
|
5 |
+
"adapter_kernel_size": 3,
|
6 |
+
"adapter_stride": 2,
|
7 |
+
"add_adapter": false,
|
8 |
+
"apply_spec_augment": true,
|
9 |
+
"architectures": [
|
10 |
+
"Wav2Vec2ForCTC"
|
11 |
+
],
|
12 |
+
"attention_dropout": 0.0,
|
13 |
+
"bos_token_id": 1,
|
14 |
+
"classifier_proj_size": 256,
|
15 |
+
"codevector_dim": 768,
|
16 |
+
"contrastive_logits_temperature": 0.1,
|
17 |
+
"conv_bias": true,
|
18 |
+
"conv_dim": [
|
19 |
+
512,
|
20 |
+
512,
|
21 |
+
512,
|
22 |
+
512,
|
23 |
+
512,
|
24 |
+
512,
|
25 |
+
512
|
26 |
+
],
|
27 |
+
"conv_kernel": [
|
28 |
+
10,
|
29 |
+
3,
|
30 |
+
3,
|
31 |
+
3,
|
32 |
+
3,
|
33 |
+
2,
|
34 |
+
2
|
35 |
+
],
|
36 |
+
"conv_stride": [
|
37 |
+
5,
|
38 |
+
2,
|
39 |
+
2,
|
40 |
+
2,
|
41 |
+
2,
|
42 |
+
2,
|
43 |
+
2
|
44 |
+
],
|
45 |
+
"ctc_loss_reduction": "mean",
|
46 |
+
"ctc_zero_infinity": false,
|
47 |
+
"diversity_loss_weight": 0.1,
|
48 |
+
"do_stable_layer_norm": true,
|
49 |
+
"eos_token_id": 2,
|
50 |
+
"feat_extract_activation": "gelu",
|
51 |
+
"feat_extract_dropout": 0.0,
|
52 |
+
"feat_extract_norm": "layer",
|
53 |
+
"feat_proj_dropout": 0.0,
|
54 |
+
"feat_quantizer_dropout": 0.0,
|
55 |
+
"final_dropout": 0.0,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.0,
|
58 |
+
"hidden_size": 1024,
|
59 |
+
"initializer_range": 0.02,
|
60 |
+
"intermediate_size": 4096,
|
61 |
+
"layer_norm_eps": 1e-05,
|
62 |
+
"layerdrop": 0.0,
|
63 |
+
"mask_feature_length": 64,
|
64 |
+
"mask_feature_min_masks": 0,
|
65 |
+
"mask_feature_prob": 0.25,
|
66 |
+
"mask_time_length": 10,
|
67 |
+
"mask_time_min_masks": 2,
|
68 |
+
"mask_time_prob": 0.75,
|
69 |
+
"model_type": "wav2vec2",
|
70 |
+
"num_adapter_layers": 3,
|
71 |
+
"num_attention_heads": 16,
|
72 |
+
"num_codevector_groups": 2,
|
73 |
+
"num_codevectors_per_group": 320,
|
74 |
+
"num_conv_pos_embedding_groups": 16,
|
75 |
+
"num_conv_pos_embeddings": 128,
|
76 |
+
"num_feat_extract_layers": 7,
|
77 |
+
"num_hidden_layers": 24,
|
78 |
+
"num_negatives": 100,
|
79 |
+
"output_hidden_size": 1024,
|
80 |
+
"pad_token_id": 38,
|
81 |
+
"proj_codevector_dim": 768,
|
82 |
+
"tdnn_dilation": [
|
83 |
+
1,
|
84 |
+
2,
|
85 |
+
3,
|
86 |
+
1,
|
87 |
+
1
|
88 |
+
],
|
89 |
+
"tdnn_dim": [
|
90 |
+
512,
|
91 |
+
512,
|
92 |
+
512,
|
93 |
+
512,
|
94 |
+
1500
|
95 |
+
],
|
96 |
+
"tdnn_kernel": [
|
97 |
+
5,
|
98 |
+
3,
|
99 |
+
3,
|
100 |
+
1,
|
101 |
+
1
|
102 |
+
],
|
103 |
+
"torch_dtype": "float32",
|
104 |
+
"transformers_version": "4.35.0",
|
105 |
+
"use_weighted_layer_sum": false,
|
106 |
+
"vocab_size": 41,
|
107 |
+
"xvector_output_dim": 512,
|
108 |
+
"zero_infinity": true
|
109 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2ac5d70bb354a00ee46322dc6e4131488fa477f4afc5552386a8a45c5121d12
|
3 |
+
size 1261975532
|
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 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"unk_token": "[UNK]"
|
6 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"37": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": true,
|
8 |
+
"single_word": false,
|
9 |
+
"special": false
|
10 |
+
},
|
11 |
+
"38": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": true,
|
16 |
+
"single_word": false,
|
17 |
+
"special": false
|
18 |
+
},
|
19 |
+
"39": {
|
20 |
+
"content": "<s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"40": {
|
28 |
+
"content": "</s>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"bos_token": "<s>",
|
37 |
+
"clean_up_tokenization_spaces": true,
|
38 |
+
"do_lower_case": false,
|
39 |
+
"eos_token": "</s>",
|
40 |
+
"model_max_length": 1000000000000000019884624838656,
|
41 |
+
"pad_token": "[PAD]",
|
42 |
+
"replace_word_delimiter_char": " ",
|
43 |
+
"target_lang": null,
|
44 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
45 |
+
"unk_token": "[UNK]",
|
46 |
+
"word_delimiter_token": "|"
|
47 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5b43488ace499f5d56f8a2781083604775bd6f8269572c6e383d8035d601997
|
3 |
+
size 4091
|
vocab.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 38,
|
3 |
+
"[UNK]": 37,
|
4 |
+
"`": 1,
|
5 |
+
"|": 0,
|
6 |
+
"ئ": 2,
|
7 |
+
"ا": 3,
|
8 |
+
"ب": 4,
|
9 |
+
"ت": 5,
|
10 |
+
"ج": 6,
|
11 |
+
"خ": 7,
|
12 |
+
"د": 8,
|
13 |
+
"ر": 9,
|
14 |
+
"ز": 10,
|
15 |
+
"س": 11,
|
16 |
+
"ش": 12,
|
17 |
+
"غ": 13,
|
18 |
+
"ف": 14,
|
19 |
+
"ق": 15,
|
20 |
+
"ك": 16,
|
21 |
+
"ل": 17,
|
22 |
+
"م": 18,
|
23 |
+
"ن": 19,
|
24 |
+
"و": 20,
|
25 |
+
"ى": 21,
|
26 |
+
"ي": 22,
|
27 |
+
"پ": 23,
|
28 |
+
"چ": 24,
|
29 |
+
"ژ": 25,
|
30 |
+
"ک": 26,
|
31 |
+
"ڭ": 27,
|
32 |
+
"گ": 28,
|
33 |
+
"ھ": 29,
|
34 |
+
"ۆ": 30,
|
35 |
+
"ۇ": 31,
|
36 |
+
"ۈ": 32,
|
37 |
+
"ۋ": 33,
|
38 |
+
"ی": 34,
|
39 |
+
"ې": 35,
|
40 |
+
"ە": 36
|
41 |
+
}
|