Hugging Face's logo

ad019el
/
tamasheq-99-final-old-crashed

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
ad019el commited on
Commit
c38b860
•
1 Parent(s): 91fa944

final

Browse files
Files changed (8) hide show
  1. config.json +117 -0
  2. preprocessor_config.json +9 -0
  3. pytorch_model.bin +3 -0
  4. runs/Aug15_17-53-51_f163a2af2bd6/events.out.tfevents.1692122092.f163a2af2bd6.3941.0 +3 -0
  5. special_tokens_map.json +6 -0
  6. tokenizer_config.json +13 -0
  7. training_args.bin +3 -0
  8. vocab.json +45 -0
config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ad019el/tamasheq-99-6",
3
+ "gradient_checkpointing": true,
4
+ "activation_dropout": 0.05,
5
+ "adapter_attn_dim": null,
6
+ "adapter_kernel_size": 3,
7
+ "adapter_stride": 2,
8
+ "add_adapter": false,
9
+ "apply_spec_augment": true,
10
+ "architectures": [
11
+ "Wav2Vec2ForCTC"
12
+ ],
13
+ "attention_dropout": 0.1,
14
+ "bos_token_id": 1,
15
+ "classifier_proj_size": 256,
16
+ "codevector_dim": 256,
17
+ "contrastive_logits_temperature": 0.1,
18
+ "conv_bias": true,
19
+ "conv_dim": [
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512,
26
+ 512
27
+ ],
28
+ "conv_kernel": [
29
+ 10,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 3,
34
+ 2,
35
+ 2
36
+ ],
37
+ "conv_stride": [
38
+ 5,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2,
44
+ 2
45
+ ],
46
+ "ctc_loss_reduction": "mean",
47
+ "ctc_zero_infinity": true,
48
+ "diversity_loss_weight": 0.1,
49
+ "do_stable_layer_norm": true,
50
+ "eos_token_id": 2,
51
+ "feat_extract_activation": "gelu",
52
+ "feat_extract_dropout": 0.0,
53
+ "feat_extract_norm": "layer",
54
+ "feat_proj_dropout": 0.0,
55
+ "feat_quantizer_dropout": 0.0,
56
+ "final_dropout": 0.0,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_size": 1024,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 4096,
62
+ "layer_norm_eps": 1e-05,
63
+ "layerdrop": 0.1,
64
+ "mask_channel_length": 10,
65
+ "mask_channel_min_space": 1,
66
+ "mask_channel_other": 0.0,
67
+ "mask_channel_prob": 0.0,
68
+ "mask_channel_selection": "static",
69
+ "mask_feature_length": 10,
70
+ "mask_feature_min_masks": 0,
71
+ "mask_feature_prob": 0.0,
72
+ "mask_time_length": 10,
73
+ "mask_time_min_masks": 2,
74
+ "mask_time_min_space": 1,
75
+ "mask_time_other": 0.0,
76
+ "mask_time_prob": 0.05,
77
+ "mask_time_selection": "static",
78
+ "model_type": "wav2vec2",
79
+ "num_adapter_layers": 3,
80
+ "num_attention_heads": 16,
81
+ "num_codevector_groups": 2,
82
+ "num_codevectors_per_group": 320,
83
+ "num_conv_pos_embedding_groups": 16,
84
+ "num_conv_pos_embeddings": 128,
85
+ "num_feat_extract_layers": 7,
86
+ "num_hidden_layers": 24,
87
+ "num_negatives": 100,
88
+ "output_hidden_size": 1024,
89
+ "pad_token_id": 42,
90
+ "proj_codevector_dim": 256,
91
+ "tdnn_dilation": [
92
+ 1,
93
+ 2,
94
+ 3,
95
+ 1,
96
+ 1
97
+ ],
98
+ "tdnn_dim": [
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 512,
103
+ 1500
104
+ ],
105
+ "tdnn_kernel": [
106
+ 5,
107
+ 3,
108
+ 3,
109
+ 1,
110
+ 1
111
+ ],
112
+ "torch_dtype": "float32",
113
+ "transformers_version": "4.31.0",
114
+ "use_weighted_layer_sum": false,
115
+ "vocab_size": 43,
116
+ "xvector_output_dim": 512
117
+ }
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": 0.0,
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 sha256:466f6c84cff35a9f68abc921855eb03fada44a827389c1b253a33840447ccaef
3
+ size 1262078125
runs/Aug15_17-53-51_f163a2af2bd6/events.out.tfevents.1692122092.f163a2af2bd6.3941.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7a88a3a24edcb10c3f1842cbe3ead25ae6ac1256ab2c576d4abbb1454eb997d
3
+ size 8530
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "replace_word_delimiter_char": " ",
9
+ "target_lang": null,
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb96442376da9c29e07c372565529befc21db5ba6630822b1a3b2ced5f51ccfb
3
+ size 3963
vocab.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 42,
3
+ "[UNK]": 41,
4
+ "|": 33,
5
+ "ء": 6,
6
+ "آ": 17,
7
+ "أ": 10,
8
+ "ؤ": 37,
9
+ "إ": 3,
10
+ "ئ": 34,
11
+ "ا": 5,
12
+ "ب": 18,
13
+ "ة": 14,
14
+ "ت": 20,
15
+ "ث": 2,
16
+ "ج": 13,
17
+ "ح": 15,
18
+ "خ": 31,
19
+ "د": 8,
20
+ "ذ": 35,
21
+ "ر": 28,
22
+ "ز": 12,
23
+ "س": 32,
24
+ "ش": 39,
25
+ "ص": 36,
26
+ "ض": 25,
27
+ "ط": 30,
28
+ "ظ": 29,
29
+ "ع": 1,
30
+ "غ": 23,
31
+ "ف": 22,
32
+ "ق": 26,
33
+ "ك": 24,
34
+ "ل": 16,
35
+ "م": 21,
36
+ "ن": 4,
37
+ "ه": 0,
38
+ "و": 9,
39
+ "ى": 40,
40
+ "ي": 38,
41
+ "ٱ": 11,
42
+ "ڤ": 7,
43
+ "ک": 19,
44
+ "ی": 27
45
+ }