Abdulwahab Sahyoun commited on
Commit
907e942
1 Parent(s): b8135d6

Training in progress, step 400

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 75, "</s>": 76}
config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
3
+ "activation_dropout": 0.0,
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": 0.0,
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": 0.1,
62
+ "mask_channel_length": 10,
63
+ "mask_channel_min_space": 1,
64
+ "mask_channel_other": 0.0,
65
+ "mask_channel_prob": 0.0,
66
+ "mask_channel_selection": "static",
67
+ "mask_feature_length": 10,
68
+ "mask_feature_min_masks": 0,
69
+ "mask_feature_prob": 0.0,
70
+ "mask_time_length": 10,
71
+ "mask_time_min_masks": 2,
72
+ "mask_time_min_space": 1,
73
+ "mask_time_other": 0.0,
74
+ "mask_time_prob": 0.05,
75
+ "mask_time_selection": "static",
76
+ "model_type": "wav2vec2",
77
+ "num_adapter_layers": 3,
78
+ "num_attention_heads": 16,
79
+ "num_codevector_groups": 2,
80
+ "num_codevectors_per_group": 320,
81
+ "num_conv_pos_embedding_groups": 16,
82
+ "num_conv_pos_embeddings": 128,
83
+ "num_feat_extract_layers": 7,
84
+ "num_hidden_layers": 24,
85
+ "num_negatives": 100,
86
+ "output_hidden_size": 1024,
87
+ "pad_token_id": 74,
88
+ "proj_codevector_dim": 768,
89
+ "tdnn_dilation": [
90
+ 1,
91
+ 2,
92
+ 3,
93
+ 1,
94
+ 1
95
+ ],
96
+ "tdnn_dim": [
97
+ 512,
98
+ 512,
99
+ 512,
100
+ 512,
101
+ 1500
102
+ ],
103
+ "tdnn_kernel": [
104
+ 5,
105
+ 3,
106
+ 3,
107
+ 1,
108
+ 1
109
+ ],
110
+ "torch_dtype": "float32",
111
+ "transformers_version": "4.18.0.dev0",
112
+ "use_weighted_layer_sum": false,
113
+ "vocab_size": 77,
114
+ "xvector_output_dim": 512
115
+ }
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 sha256:7be89a5d86098a57c1d763b223ae7547de292ced95ad00bae6b7dea2d2999d80
3
+ size 1262241969
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
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": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": null, "name_or_path": "/l/users/abdulwahab.sahyoun/aradia/aradia-ctc-v1", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8a34371d1344fd7bbc3fcc02ceedb64c7f5623d7c7c8abee5c7efedc86bf3e8
3
+ size 3055
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"ء": 1, "ؤ": 2, "ئ": 3, "ا": 4, "ب": 5, "ة": 6, "ت": 7, "ث": 8, "ج": 9, "ح": 10, "خ": 11, "د": 12, "ذ": 13, "ر": 14, "ز": 15, "س": 16, "ش": 17, "ص": 18, "ض": 19, "ط": 20, "ظ": 21, "ع": 22, "غ": 23, "ف": 24, "ق": 25, "ك": 26, "ل": 27, "م": 28, "ن": 29, "ه": 30, "و": 31, "ى": 32, "ي": 33, "پ": 34, "چ": 35, "ڤ": 36, "ک": 37, "ڭ": 38, "گ": 39, "ۃ": 40, "ی": 41, "ﷲ": 42, "ﷺ": 43, "ﺎ": 44, "ﺐ": 45, "ﺑ": 46, "ﺔ": 47, "ﺖ": 48, "ﺗ": 49, "ﺘ": 50, "ﺠ": 51, "ﺨ": 52, "ﺮ": 53, "ﺸ": 54, "ﺻ": 55, "ﻀ": 56, "ﻂ": 57, "ﻄ": 58, "ﻋ": 59, "ﻌ": 60, "ﻔ": 61, "ﻗ": 62, "ﻘ": 63, "ﻚ": 64, "ﻟ": 65, "ﻠ": 66, "ﻢ": 67, "ﻤ": 68, "ﻨ": 69, "ﻮ": 70, "ﻳ": 71, "ﻴ": 72, "|": 0, "[UNK]": 73, "[PAD]": 74}