nouamanetazi HF staff commited on
Commit
f22047c
1 Parent(s): 800e56c

Model save

Browse files
.ipynb_checkpoints/added_tokens-checkpoint.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 33, "</s>": 34}
.ipynb_checkpoints/all_results-checkpoint.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 26.253612518310547,
4
+ "eval_runtime": 5.982,
5
+ "eval_samples": 128,
6
+ "eval_samples_per_second": 21.397,
7
+ "eval_steps_per_second": 0.334,
8
+ "eval_wer": 1.0,
9
+ "total_flos": 1.3476444758728704e+17,
10
+ "train_loss": 19.624227905273436,
11
+ "train_runtime": 37.1321,
12
+ "train_samples": 128,
13
+ "train_samples_per_second": 17.236,
14
+ "train_steps_per_second": 0.269
15
+ }
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
+ "activation_dropout": 0.1,
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": 0.0,
62
+ "mask_feature_length": 64,
63
+ "mask_feature_min_masks": 0,
64
+ "mask_feature_prob": 0.25,
65
+ "mask_time_length": 10,
66
+ "mask_time_min_masks": 2,
67
+ "mask_time_prob": 0.75,
68
+ "model_type": "wav2vec2",
69
+ "num_adapter_layers": 3,
70
+ "num_attention_heads": 16,
71
+ "num_codevector_groups": 2,
72
+ "num_codevectors_per_group": 320,
73
+ "num_conv_pos_embedding_groups": 16,
74
+ "num_conv_pos_embeddings": 128,
75
+ "num_feat_extract_layers": 7,
76
+ "num_hidden_layers": 24,
77
+ "num_negatives": 100,
78
+ "output_hidden_size": 1024,
79
+ "pad_token_id": 32,
80
+ "proj_codevector_dim": 768,
81
+ "tdnn_dilation": [
82
+ 1,
83
+ 2,
84
+ 3,
85
+ 1,
86
+ 1
87
+ ],
88
+ "tdnn_dim": [
89
+ 512,
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 1500
94
+ ],
95
+ "tdnn_kernel": [
96
+ 5,
97
+ 3,
98
+ 3,
99
+ 1,
100
+ 1
101
+ ],
102
+ "torch_dtype": "float32",
103
+ "transformers_version": "4.17.0.dev0",
104
+ "use_weighted_layer_sum": false,
105
+ "vocab_size": 35,
106
+ "xvector_output_dim": 512
107
+ }
.ipynb_checkpoints/preprocessor_config-checkpoint.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
+ }
.ipynb_checkpoints/vocab-checkpoint.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"_": 1, "e": 2, "g": 3, "t": 4, "\u00ab": 5, "\u00bb": 6, "\u061b": 7, "\u0621": 8, "\u0627": 9, "\u0628": 10, "\u0629": 11, "\u062a": 12, "\u062b": 13, "\u062c": 14, "\u062d": 15, "\u062e": 16, "\u062f": 17, "\u0630": 18, "\u0631": 19, "\u0632": 20, "\u0633": 21, "\u0634": 22, "\u0635": 23, "\u0636": 24, "\u0637": 25, "\u0638": 26, "\u0639": 27, "\u063a": 28, "\u0641": 29, "\u0642": 30, "\u0643": 31, "\u0644": 32, "\u0645": 33, "\u0646": 34, "\u0647": 35, "\u0648": 36, "\u064a": 37, "\u0670": 38, "\u0686": 39, "\u06a8": 40, "\u06a9": 41, "\u06be": 42, "\u06cc": 43, "\u06d6": 44, "\u06da": 45, "\u262d": 46, "\ufe83": 47, "\ufefb": 48, "|": 0, "[UNK]": 49, "[PAD]": 50}
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 33, "</s>": 34}
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c4082788c9d6d96db95ff984438a50bc73180dbf35fc83928d83d3220f26827
3
  size 1262067185
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03187d4fdffd6bfd6668c712b8b34435c8b8fd1d873425a1d3179c6faaa1434c
3
  size 1262067185
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}]}
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": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./wav2vec2-xls-r-300m-ar", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8de68d45534d5a90ee834f62519d83f796fc9d6c73809f34cd5e00ed1cf310be
3
  size 3055
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75f86ca385bb82aeecbcfec2b42d4f24ce3dfaaa81f2eaa0da96c75d5dc881f6
3
  size 3055
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"ء": 1, "ا": 2, "ب": 3, "ة": 4, "ت": 5, "ث": 6, "ج": 7, "ح": 8, "خ": 9, "د": 10, "ذ": 11, "ر": 12, "ز": 13, "س": 14, "ش": 15, "ص": 16, "ض": 17, "ط": 18, "ظ": 19, "ع": 20, "غ": 21, "ف": 22, "ق": 23, "ك": 24, "ل": 25, "م": 26, "ن": 27, "ه": 28, "و": 29, "ي": 30, "|": 0, "[UNK]": 31, "[PAD]": 32}