Bakhtiar56
commited on
Commit
•
c80a2a7
1
Parent(s):
2f0a5f1
Training in progress, step 400
Browse files- added_tokens.json +4 -0
- config.json +116 -0
- model.safetensors +3 -0
- preprocessor_config.json +10 -0
- runs/Sep06_10-04-17_nvidia-gpu-machine/events.out.tfevents.1725610146.nvidia-gpu-machine +3 -0
- special_tokens_map.json +30 -0
- tokenizer_config.json +48 -0
- training_args.bin +3 -0
- vocab.json +110 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 109,
|
3 |
+
"<s>": 108
|
4 |
+
}
|
config.json
ADDED
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
3 |
+
"activation_dropout": 0.0,
|
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_channel_length": 10,
|
64 |
+
"mask_channel_min_space": 1,
|
65 |
+
"mask_channel_other": 0.0,
|
66 |
+
"mask_channel_prob": 0.0,
|
67 |
+
"mask_channel_selection": "static",
|
68 |
+
"mask_feature_length": 10,
|
69 |
+
"mask_feature_min_masks": 0,
|
70 |
+
"mask_feature_prob": 0.0,
|
71 |
+
"mask_time_length": 10,
|
72 |
+
"mask_time_min_masks": 2,
|
73 |
+
"mask_time_min_space": 1,
|
74 |
+
"mask_time_other": 0.0,
|
75 |
+
"mask_time_prob": 0.05,
|
76 |
+
"mask_time_selection": "static",
|
77 |
+
"model_type": "wav2vec2",
|
78 |
+
"num_adapter_layers": 3,
|
79 |
+
"num_attention_heads": 16,
|
80 |
+
"num_codevector_groups": 2,
|
81 |
+
"num_codevectors_per_group": 320,
|
82 |
+
"num_conv_pos_embedding_groups": 16,
|
83 |
+
"num_conv_pos_embeddings": 128,
|
84 |
+
"num_feat_extract_layers": 7,
|
85 |
+
"num_hidden_layers": 24,
|
86 |
+
"num_negatives": 100,
|
87 |
+
"output_hidden_size": 1024,
|
88 |
+
"pad_token_id": 107,
|
89 |
+
"proj_codevector_dim": 768,
|
90 |
+
"tdnn_dilation": [
|
91 |
+
1,
|
92 |
+
2,
|
93 |
+
3,
|
94 |
+
1,
|
95 |
+
1
|
96 |
+
],
|
97 |
+
"tdnn_dim": [
|
98 |
+
512,
|
99 |
+
512,
|
100 |
+
512,
|
101 |
+
512,
|
102 |
+
1500
|
103 |
+
],
|
104 |
+
"tdnn_kernel": [
|
105 |
+
5,
|
106 |
+
3,
|
107 |
+
3,
|
108 |
+
1,
|
109 |
+
1
|
110 |
+
],
|
111 |
+
"torch_dtype": "float32",
|
112 |
+
"transformers_version": "4.45.0.dev0",
|
113 |
+
"use_weighted_layer_sum": false,
|
114 |
+
"vocab_size": 110,
|
115 |
+
"xvector_output_dim": 512
|
116 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5181f69a430b18c31201717f511c253e706d1b83083a487f5b6e287c8599220b
|
3 |
+
size 1262258480
|
preprocessor_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0,
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
+
"return_attention_mask": true,
|
9 |
+
"sampling_rate": 16000
|
10 |
+
}
|
runs/Sep06_10-04-17_nvidia-gpu-machine/events.out.tfevents.1725610146.nvidia-gpu-machine
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2ca7e30f8db2c51dc209216f18240c34174fed96a4cc95e88459520b2665c48
|
3 |
+
size 7528
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": true,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": true,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "[UNK]",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": true,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"106": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": true,
|
8 |
+
"single_word": false,
|
9 |
+
"special": false
|
10 |
+
},
|
11 |
+
"107": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": true,
|
16 |
+
"single_word": false,
|
17 |
+
"special": false
|
18 |
+
},
|
19 |
+
"108": {
|
20 |
+
"content": "<s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"109": {
|
28 |
+
"content": "</s>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
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 |
+
"processor_class": "Wav2Vec2Processor",
|
43 |
+
"replace_word_delimiter_char": " ",
|
44 |
+
"target_lang": null,
|
45 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
46 |
+
"unk_token": "[UNK]",
|
47 |
+
"word_delimiter_token": "|"
|
48 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b080801316ca1ab9c2d95d7cfbdf9bfc5847f9330d348e56121d18b3a9d61259
|
3 |
+
size 5240
|
vocab.json
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 107,
|
3 |
+
"[UNK]": 106,
|
4 |
+
"_": 1,
|
5 |
+
"`": 2,
|
6 |
+
"a": 3,
|
7 |
+
"b": 4,
|
8 |
+
"c": 5,
|
9 |
+
"d": 6,
|
10 |
+
"e": 7,
|
11 |
+
"f": 8,
|
12 |
+
"h": 9,
|
13 |
+
"i": 10,
|
14 |
+
"k": 11,
|
15 |
+
"l": 12,
|
16 |
+
"m": 13,
|
17 |
+
"n": 14,
|
18 |
+
"q": 15,
|
19 |
+
"r": 16,
|
20 |
+
"t": 17,
|
21 |
+
"u": 18,
|
22 |
+
"w": 19,
|
23 |
+
"y": 20,
|
24 |
+
"|": 0,
|
25 |
+
"،": 21,
|
26 |
+
"ؐ": 22,
|
27 |
+
"ؑ": 23,
|
28 |
+
"ؓ": 24,
|
29 |
+
"ؔ": 25,
|
30 |
+
"؛": 26,
|
31 |
+
"؟": 27,
|
32 |
+
"ء": 28,
|
33 |
+
"آ": 29,
|
34 |
+
"أ": 30,
|
35 |
+
"ؤ": 31,
|
36 |
+
"ئ": 32,
|
37 |
+
"ا": 33,
|
38 |
+
"ب": 34,
|
39 |
+
"ت": 35,
|
40 |
+
"ث": 36,
|
41 |
+
"ج": 37,
|
42 |
+
"ح": 38,
|
43 |
+
"خ": 39,
|
44 |
+
"د": 40,
|
45 |
+
"ذ": 41,
|
46 |
+
"ر": 42,
|
47 |
+
"ز": 43,
|
48 |
+
"س": 44,
|
49 |
+
"ش": 45,
|
50 |
+
"ص": 46,
|
51 |
+
"ض": 47,
|
52 |
+
"ط": 48,
|
53 |
+
"ظ": 49,
|
54 |
+
"ع": 50,
|
55 |
+
"غ": 51,
|
56 |
+
"ف": 52,
|
57 |
+
"ق": 53,
|
58 |
+
"ك": 54,
|
59 |
+
"ل": 55,
|
60 |
+
"م": 56,
|
61 |
+
"ن": 57,
|
62 |
+
"ه": 58,
|
63 |
+
"و": 59,
|
64 |
+
"ى": 60,
|
65 |
+
"ي": 61,
|
66 |
+
"ً": 62,
|
67 |
+
"َ": 63,
|
68 |
+
"ُ": 64,
|
69 |
+
"ِ": 65,
|
70 |
+
"ّ": 66,
|
71 |
+
"ْ": 67,
|
72 |
+
"ٓ": 68,
|
73 |
+
"ٔ": 69,
|
74 |
+
"ٗ": 70,
|
75 |
+
"ٰ": 71,
|
76 |
+
"ٴ": 72,
|
77 |
+
"ٹ": 73,
|
78 |
+
"پ": 74,
|
79 |
+
"چ": 75,
|
80 |
+
"ڈ": 76,
|
81 |
+
"ڑ": 77,
|
82 |
+
"ژ": 78,
|
83 |
+
"ک": 79,
|
84 |
+
"گ": 80,
|
85 |
+
"ں": 81,
|
86 |
+
"ھ": 82,
|
87 |
+
"ہ": 83,
|
88 |
+
"ۂ": 84,
|
89 |
+
"ۃ": 85,
|
90 |
+
"ی": 86,
|
91 |
+
"ے": 87,
|
92 |
+
"ۓ": 88,
|
93 |
+
"۔": 89,
|
94 |
+
"’": 90,
|
95 |
+
"…": 91,
|
96 |
+
"ﭨ": 92,
|
97 |
+
"ﮭ": 93,
|
98 |
+
"ﮯ": 94,
|
99 |
+
"ﯾ": 95,
|
100 |
+
"ﷲ": 96,
|
101 |
+
"ﷺ": 97,
|
102 |
+
"ﺅ": 98,
|
103 |
+
"ﺗ": 99,
|
104 |
+
"ﺘ": 100,
|
105 |
+
"ﺩ": 101,
|
106 |
+
"ﺲ": 102,
|
107 |
+
"ﻧ": 103,
|
108 |
+
"ﻮ": 104,
|
109 |
+
"!": 105
|
110 |
+
}
|