Badr Abdullah commited on
Commit
26a9a80
1 Parent(s): a33a7b2

Training in progress, step 400

Browse files
config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "utter-project/mHuBERT-147",
3
+ "activation_dropout": 0.1,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForCTC"
11
+ ],
12
+ "attention_dropout": 0.0,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 256,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": false,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "mean",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": false,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "group",
53
+ "feat_proj_dropout": 0.0,
54
+ "feat_proj_layer_norm": true,
55
+ "feat_quantizer_dropout": 0.0,
56
+ "final_dropout": 0.1,
57
+ "gradient_checkpointing": false,
58
+ "hidden_act": "gelu",
59
+ "hidden_dropout": 0.0,
60
+ "hidden_dropout_prob": 0.1,
61
+ "hidden_size": 768,
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 3072,
64
+ "layer_norm_eps": 1e-05,
65
+ "layerdrop": 0.0,
66
+ "mask_feature_length": 10,
67
+ "mask_feature_min_masks": 0,
68
+ "mask_feature_prob": 0.0,
69
+ "mask_time_length": 10,
70
+ "mask_time_min_masks": 2,
71
+ "mask_time_prob": 0.05,
72
+ "model_type": "wav2vec2",
73
+ "num_adapter_layers": 3,
74
+ "num_attention_heads": 12,
75
+ "num_codevector_groups": 2,
76
+ "num_codevectors_per_group": 320,
77
+ "num_conv_pos_embedding_groups": 16,
78
+ "num_conv_pos_embeddings": 128,
79
+ "num_feat_extract_layers": 7,
80
+ "num_hidden_layers": 12,
81
+ "num_negatives": 100,
82
+ "output_hidden_size": 768,
83
+ "pad_token_id": 41,
84
+ "proj_codevector_dim": 256,
85
+ "tdnn_dilation": [
86
+ 1,
87
+ 2,
88
+ 3,
89
+ 1,
90
+ 1
91
+ ],
92
+ "tdnn_dim": [
93
+ 512,
94
+ 512,
95
+ 512,
96
+ 512,
97
+ 1500
98
+ ],
99
+ "tdnn_kernel": [
100
+ 5,
101
+ 3,
102
+ 3,
103
+ 1,
104
+ 1
105
+ ],
106
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
107
+ "torch_dtype": "float32",
108
+ "transformers_version": "4.42.0.dev0",
109
+ "use_weighted_layer_sum": false,
110
+ "vocab_size": 44,
111
+ "xvector_output_dim": 512
112
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73ff204e1040eae997e0f12e0b1b82d40be0d069605c4d5551a608c1a8f45976
3
+ size 377648040
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a2dad4740ac6a4a128384c8535c15c966c50f10f8966192cb512675fc3c24f6
3
+ size 5176