achmadridhooo commited on
Commit
1101e52
1 Parent(s): 678acfc

Language Model

Browse files
config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
3
+ "activation_dropout": 0.0,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "Wav2Vec2ForCTC"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "codevector_dim": 768,
12
+ "contrastive_logits_temperature": 0.1,
13
+ "conv_bias": true,
14
+ "conv_dim": [
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512
22
+ ],
23
+ "conv_kernel": [
24
+ 10,
25
+ 3,
26
+ 3,
27
+ 3,
28
+ 3,
29
+ 2,
30
+ 2
31
+ ],
32
+ "conv_stride": [
33
+ 5,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2
40
+ ],
41
+ "ctc_loss_reduction": "mean",
42
+ "ctc_zero_infinity": false,
43
+ "diversity_loss_weight": 0.1,
44
+ "do_stable_layer_norm": true,
45
+ "eos_token_id": 2,
46
+ "feat_extract_activation": "gelu",
47
+ "feat_extract_dropout": 0.0,
48
+ "feat_extract_norm": "layer",
49
+ "feat_proj_dropout": 0.1,
50
+ "feat_quantizer_dropout": 0.0,
51
+ "final_dropout": 0.0,
52
+ "gradient_checkpointing": false,
53
+ "hidden_act": "gelu",
54
+ "hidden_dropout": 0.1,
55
+ "hidden_size": 1024,
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": 4096,
58
+ "layer_norm_eps": 1e-05,
59
+ "layerdrop": 0.1,
60
+ "mask_channel_length": 10,
61
+ "mask_channel_min_space": 1,
62
+ "mask_channel_other": 0.0,
63
+ "mask_channel_prob": 0.0,
64
+ "mask_channel_selection": "static",
65
+ "mask_feature_length": 10,
66
+ "mask_feature_prob": 0.0,
67
+ "mask_time_length": 10,
68
+ "mask_time_min_space": 1,
69
+ "mask_time_other": 0.0,
70
+ "mask_time_prob": 0.075,
71
+ "mask_time_selection": "static",
72
+ "model_type": "wav2vec2",
73
+ "num_attention_heads": 16,
74
+ "num_codevector_groups": 2,
75
+ "num_codevectors_per_group": 320,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 24,
80
+ "num_negatives": 100,
81
+ "pad_token_id": 29,
82
+ "proj_codevector_dim": 768,
83
+ "torch_dtype": "float32",
84
+ "transformers_version": "4.11.3",
85
+ "use_weighted_layer_sum": false,
86
+ "vocab_size": 32
87
+ }
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": false,
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:b0a28a4c25e209b776a94ba726ca44a1d182884aa9e6246c47b1295373379fa7
3
+ size 1262054897
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ea90ba5e0b2165f883aeb7c8d5f92c30730488cf70970a676fd32d821f2135e
3
+ size 14567
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
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": "|"}
trainer_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 27.499770766473556,
5
+ "global_step": 1319604,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [],
10
+ "max_steps": 4798600,
11
+ "num_train_epochs": 100,
12
+ "total_flos": 1.9718623298510505e+21,
13
+ "trial_name": null,
14
+ "trial_params": null
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b79768bdbeba1586fe835d968f78cdb388c63ee7db62cd892b77f5e8bb4d311
3
+ size 2863
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {" ": 21, "'": 13, "a": 24, "b": 17, "c": 25, "d": 2, "e": 9, "f": 14, "g": 22, "h": 8, "i": 4, "j": 18, "k": 5, "l": 16, "m": 6, "n": 7, "o": 10, "p": 19, "q": 3, "r": 20, "s": 11, "t": 0, "u": 26, "v": 27, "w": 1, "x": 23, "y": 15, "z": 12, "[UNK]": 28, "[PAD]": 29, "|": 30}