Hugging Face's logo

hr16
/
wav2vec2-base-vi-vispeech-classifier-v1

Transformers
TensorBoard
Safetensors
wav2vec2
Inference Endpoints
Model card Files Metrics Community
hr16 commited on
Commit
dd7a553
·
verified ·
1 Parent(s): af5d994

Training in progress, epoch 1

Browse files
Files changed (13) hide show
  1. config.json +130 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +10 -0
  4. runs/Jul11_03-42-11_187431d6b99b/events.out.tfevents.1720669332.187431d6b99b.34.0 +3 -0
  5. runs/Jul11_03-43-49_187431d6b99b/events.out.tfevents.1720669430.187431d6b99b.371.0 +3 -0
  6. runs/Jul11_03-46-08_187431d6b99b/events.out.tfevents.1720669569.187431d6b99b.481.0 +3 -0
  7. runs/Jul11_04-08-06_187431d6b99b/events.out.tfevents.1720670887.187431d6b99b.1176.0 +3 -0
  8. runs/Jul11_04-11-30_187431d6b99b/events.out.tfevents.1720671091.187431d6b99b.1519.0 +3 -0
  9. runs/Jul11_04-29-18_187431d6b99b/events.out.tfevents.1720672159.187431d6b99b.2284.0 +3 -0
  10. runs/Jul11_04-30-49_187431d6b99b/events.out.tfevents.1720672250.187431d6b99b.2437.0 +3 -0
  11. runs/Jul11_04-32-28_187431d6b99b/events.out.tfevents.1720672349.187431d6b99b.2588.0 +3 -0
  12. runs/Jul11_04-33-33_187431d6b99b/events.out.tfevents.1720672414.187431d6b99b.2699.0 +3 -0
  13. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nguyenvulebinh/wav2vec2-base-vi",
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
+ "Wav2Vec2ForViSpeechClassification"
11
+ ],
12
+ "attention_dropout": 0.1,
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": "sum",
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": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.1,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_dropout_prob": 0.1,
60
+ "hidden_size": 768,
61
+ "id2label": {
62
+ "0": "male, northern dialect",
63
+ "1": "male, central dialect",
64
+ "2": "male, highland central dialect",
65
+ "3": "male, southern dialect",
66
+ "4": "female, northern dialect",
67
+ "5": "female, central dialect",
68
+ "6": "female, highland central dialect",
69
+ "7": "female, southern dialect"
70
+ },
71
+ "initializer_range": 0.02,
72
+ "intermediate_size": 3072,
73
+ "label2id": {
74
+ "female, central dialect": "5",
75
+ "female, highland central dialect": "6",
76
+ "female, northern dialect": "4",
77
+ "female, southern dialect": "7",
78
+ "male, central dialect": "1",
79
+ "male, highland central dialect": "2",
80
+ "male, northern dialect": "0",
81
+ "male, southern dialect": "3"
82
+ },
83
+ "layer_norm_eps": 1e-05,
84
+ "layerdrop": 0.1,
85
+ "mask_feature_length": 10,
86
+ "mask_feature_min_masks": 0,
87
+ "mask_feature_prob": 0.0,
88
+ "mask_time_length": 10,
89
+ "mask_time_min_masks": 2,
90
+ "mask_time_prob": 0.05,
91
+ "model_type": "wav2vec2",
92
+ "num_adapter_layers": 3,
93
+ "num_attention_heads": 12,
94
+ "num_codevector_groups": 2,
95
+ "num_codevectors_per_group": 320,
96
+ "num_conv_pos_embedding_groups": 16,
97
+ "num_conv_pos_embeddings": 128,
98
+ "num_feat_extract_layers": 7,
99
+ "num_hidden_layers": 12,
100
+ "num_negatives": 100,
101
+ "output_hidden_size": 768,
102
+ "pad_token_id": 0,
103
+ "proj_codevector_dim": 256,
104
+ "tdnn_dilation": [
105
+ 1,
106
+ 2,
107
+ 3,
108
+ 1,
109
+ 1
110
+ ],
111
+ "tdnn_dim": [
112
+ 512,
113
+ 512,
114
+ 512,
115
+ 512,
116
+ 1500
117
+ ],
118
+ "tdnn_kernel": [
119
+ 5,
120
+ 3,
121
+ 3,
122
+ 1,
123
+ 1
124
+ ],
125
+ "torch_dtype": "float32",
126
+ "transformers_version": "4.41.2",
127
+ "use_weighted_layer_sum": false,
128
+ "vocab_size": 96,
129
+ "xvector_output_dim": 512
130
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f12518914db208eb0fa67d8b3f3bc565d74ff47083b531938fb45bd93ca602f4
3
+ size 383295784
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
+ }
runs/Jul11_03-42-11_187431d6b99b/events.out.tfevents.1720669332.187431d6b99b.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb1c6c5527f469a10402932a137a379a8a998c376f8aafb5d3a125cc0a04234b
3
+ size 4184
runs/Jul11_03-43-49_187431d6b99b/events.out.tfevents.1720669430.187431d6b99b.371.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89b672d8e4b6852d8269df25c2836436d36646c77819df7ebb3965ad13352b96
3
+ size 4184
runs/Jul11_03-46-08_187431d6b99b/events.out.tfevents.1720669569.187431d6b99b.481.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d1a71f54ef65ad121347e8be4fa227a50f1d68c4e82d871b32f23b0c0ddaee2
3
+ size 16416
runs/Jul11_04-08-06_187431d6b99b/events.out.tfevents.1720670887.187431d6b99b.1176.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f0750c3e295352065f494daa2dfa353d91202e7f256720310f5b45826bbabbe
3
+ size 8677
runs/Jul11_04-11-30_187431d6b99b/events.out.tfevents.1720671091.187431d6b99b.1519.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87591662d9ea771025b67e7af0010be7b75b0f6201136dc8f3ef939ee9221452
3
+ size 19793
runs/Jul11_04-29-18_187431d6b99b/events.out.tfevents.1720672159.187431d6b99b.2284.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48f46effec51f474e9c0b5e4030872edeca77284843322c0dac4ee3baa7d13e9
3
+ size 4184
runs/Jul11_04-30-49_187431d6b99b/events.out.tfevents.1720672250.187431d6b99b.2437.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:606905cd3e90b7acace71e1c7b4d17f0b6e115fd6f7c9facc14fbff7552d0074
3
+ size 7643
runs/Jul11_04-32-28_187431d6b99b/events.out.tfevents.1720672349.187431d6b99b.2588.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b85714a274cc3ae4a36f7b98b6b547a3720ab63eaa491134ecce56efaac7deb
3
+ size 4184
runs/Jul11_04-33-33_187431d6b99b/events.out.tfevents.1720672414.187431d6b99b.2699.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14661fdff6059d0ffe64f40712397e92bff39f517b75232eccfefe94d54429f4
3
+ size 69068
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ba97f7b1f10cd162ad6bf52e8c146f3093ebeb9e721883c8b1580d0f18dd26b
3
+ size 5176