Hugging Face's logo

dolphinnlp
/
wav2vec2vncskh

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
Metrics Community
infi commited on
Commit
adb48c7
·
1 Parent(s): c14a9d3

End of training

Browse files
Files changed (11) hide show
  1. README.md +61 -0
  2. config.json +109 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +9 -0
  5. runs/Dec31_08-22-21_59294992e494/events.out.tfevents.1704011170.59294992e494.1802.0 +3 -0
  6. runs/Dec31_08-26-57_59294992e494/events.out.tfevents.1704011285.59294992e494.1802.1 +3 -0
  7. runs/Dec31_08-29-41_59294992e494/events.out.tfevents.1704011451.59294992e494.1802.2 +3 -0
  8. runs/Dec31_08-35-20_59294992e494/events.out.tfevents.1704011739.59294992e494.1802.3 +3 -0
  9. runs/Dec31_08-36-00_59294992e494/events.out.tfevents.1704011784.59294992e494.1802.4 +3 -0
  10. runs/Dec31_08-36-00_59294992e494/events.out.tfevents.1704012352.59294992e494.1802.5 +3 -0
  11. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: nguyenvulebinh/wav2vec2-base-vietnamese-250h
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: wav2vec2vncskh
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # wav2vec2vncskh
17
+
18
+ This model is a fine-tuned version of [nguyenvulebinh/wav2vec2-base-vietnamese-250h](https://huggingface.co/nguyenvulebinh/wav2vec2-base-vietnamese-250h) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.2354
21
+ - Wer: 0.3651
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0001
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 1000
47
+ - num_epochs: 30
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
54
+ | 1.5055 | 15.62 | 500 | 1.2354 | 0.3651 |
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - Transformers 4.36.2
60
+ - Pytorch 2.1.0+cu121
61
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nguyenvulebinh/wav2vec2-base-vietnamese-250h",
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": 0.1,
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": "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": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.1,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_dropout_prob": 0.1,
59
+ "hidden_size": 768,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 3072,
62
+ "layer_norm_eps": 1e-05,
63
+ "layerdrop": 0.1,
64
+ "mask_feature_length": 10,
65
+ "mask_feature_min_masks": 0,
66
+ "mask_feature_prob": 0.0,
67
+ "mask_time_length": 10,
68
+ "mask_time_min_masks": 2,
69
+ "mask_time_prob": 0.05,
70
+ "model_type": "wav2vec2",
71
+ "num_adapter_layers": 3,
72
+ "num_attention_heads": 12,
73
+ "num_codevector_groups": 2,
74
+ "num_codevectors_per_group": 320,
75
+ "num_conv_pos_embedding_groups": 16,
76
+ "num_conv_pos_embeddings": 128,
77
+ "num_feat_extract_layers": 7,
78
+ "num_hidden_layers": 12,
79
+ "num_negatives": 100,
80
+ "output_hidden_size": 768,
81
+ "pad_token_id": 109,
82
+ "proj_codevector_dim": 256,
83
+ "tdnn_dilation": [
84
+ 1,
85
+ 2,
86
+ 3,
87
+ 1,
88
+ 1
89
+ ],
90
+ "tdnn_dim": [
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 512,
95
+ 1500
96
+ ],
97
+ "tdnn_kernel": [
98
+ 5,
99
+ 3,
100
+ 3,
101
+ 1,
102
+ 1
103
+ ],
104
+ "torch_dtype": "float32",
105
+ "transformers_version": "4.36.2",
106
+ "use_weighted_layer_sum": false,
107
+ "vocab_size": 110,
108
+ "xvector_output_dim": 512
109
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b594b13128de6b764c91f9427804c06eff246e63792e8ededd43e3ebaa99cc96
3
+ size 377851056
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
+ }
runs/Dec31_08-22-21_59294992e494/events.out.tfevents.1704011170.59294992e494.1802.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e9aee5cf8a28af30fb008613468bb58eefca0b6a901e430001c3e42c0590ba0
3
+ size 5803
runs/Dec31_08-26-57_59294992e494/events.out.tfevents.1704011285.59294992e494.1802.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7797884f58b0bddbf2c4f97585c4136d586de9766e0b4db26208d76c2b0e24b8
3
+ size 5803
runs/Dec31_08-29-41_59294992e494/events.out.tfevents.1704011451.59294992e494.1802.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15e85804273b3d2d83a02d803aa5c59a9fd5e596534725e261b9674f12699105
3
+ size 5803
runs/Dec31_08-35-20_59294992e494/events.out.tfevents.1704011739.59294992e494.1802.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:581091aab599a93a9576f1ca0b102879df899188849494059e694f8a96682532
3
+ size 5803
runs/Dec31_08-36-00_59294992e494/events.out.tfevents.1704011784.59294992e494.1802.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b35991111b42fa11a2b409e5cd54a1c08dc208290fd041c48e603ea1690a62e
3
+ size 5961
runs/Dec31_08-36-00_59294992e494/events.out.tfevents.1704012352.59294992e494.1802.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfcfb46ea1ef19e552446b05001ff386c161b3c7d0629e3baf79e7823a777e5a
3
+ size 6633
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf72895e9243b97f3fd7289213ccb42cedb7e4743ad91e65e871edfcb25ffd7
3
+ size 4664