mohamed1ai commited on
Commit
aed7a50
1 Parent(s): 716b277

add arabic model

Browse files
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": 0.1,
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": 0.05,
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": 36,
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": "4.16.2",
112
+ "use_weighted_layer_sum": false,
113
+ "vocab_size": 37,
114
+ "xvector_output_dim": 512
115
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a5438caadb5af2ea933c1de94f3f9950ee0f6b97b5180f36d651fdd88509463
3
+ size 2490362385
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": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5406885859307fbe939245dbb86c7e555b0b4368e461de18e55edc97b0a4cefa
3
+ size 1262075377
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf64fb7b54a451590e26f6c04910ceee2c3ce27d9e1b6166c4789f4625fa1dfb
3
+ size 14567
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fadfa6df2e109e3163e54674a5cfaf0521decee799dcc360823a398ffc8a721
3
+ size 559
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17021d32677a589959577db7e07f1a6f6cc4f5853ac51662013d08420c040379
3
+ size 623
trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.30232558139535,
5
+ "global_step": 1200,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 3.1,
12
+ "learning_rate": 7.920000000000001e-05,
13
+ "loss": 9.9787,
14
+ "step": 400
15
+ },
16
+ {
17
+ "epoch": 3.1,
18
+ "eval_loss": 3.0419623851776123,
19
+ "eval_runtime": 81.9377,
20
+ "eval_samples_per_second": 23.323,
21
+ "eval_steps_per_second": 2.917,
22
+ "eval_wer": 1.0,
23
+ "step": 400
24
+ },
25
+ {
26
+ "epoch": 6.2,
27
+ "learning_rate": 6.253164556962025e-05,
28
+ "loss": 2.7264,
29
+ "step": 800
30
+ },
31
+ {
32
+ "epoch": 6.2,
33
+ "eval_loss": 1.3224282264709473,
34
+ "eval_runtime": 81.6615,
35
+ "eval_samples_per_second": 23.401,
36
+ "eval_steps_per_second": 2.927,
37
+ "eval_wer": 1.067686658506732,
38
+ "step": 800
39
+ },
40
+ {
41
+ "epoch": 9.3,
42
+ "learning_rate": 1.189873417721519e-05,
43
+ "loss": 0.9607,
44
+ "step": 1200
45
+ },
46
+ {
47
+ "epoch": 9.3,
48
+ "eval_loss": 0.6051472425460815,
49
+ "eval_runtime": 80.842,
50
+ "eval_samples_per_second": 23.639,
51
+ "eval_steps_per_second": 2.956,
52
+ "eval_wer": 0.7376988984088128,
53
+ "step": 1200
54
+ }
55
+ ],
56
+ "max_steps": 1290,
57
+ "num_train_epochs": 10,
58
+ "total_flos": 4.3671042896313257e+18,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac244823f4a70e3609083f010fe13184f4bc0082f7aa9603beda9a2337ee36c1
3
+ size 3183
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"\u0628": 0, "\u0626": 1, "\u0631": 2, "\u062a": 3, "\u062f": 4, "\u0646": 5, "\u063a": 6, "\u0634": 7, "\u0642": 8, "\u0647": 9, "\u064a": 10, "\u0629": 11, "\u0638": 12, "\u062b": 13, "\u0630": 14, "\u0641": 15, "\u0635": 17, "\u0639": 18, "\u0633": 19, "\u0648": 20, "\u062c": 21, "\u0645": 22, "\u0624": 23, "\u0632": 24, "\u0644": 25, "\u0627": 26, "\u0649": 27, "\u0621": 28, "\u062e": 29, "\u06cc": 30, "\u0643": 31, "\u0637": 32, "\u062d": 33, "\u0636": 34, "|": 16, "[UNK]": 35, "[PAD]": 36}