Hugging Face's logo

zacdan4801
/
wav2vec2-lv-60-espeak-cv-ft-custom_vocab-OtherDiacritics-ds-f1

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
 Metrics Community
zacdan4801 commited on
Commit
54f6a88
·
verified ·
1 Parent(s): 05cbaa1

End of training

Browse files
Files changed (6) hide show
  1. README.md +103 -0
  2. config.json +116 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +9 -0
  5. runs/Apr16_20-06-48_Lydia/events.out.tfevents.1776388046.Lydia.22384.2 +3 -0
  6. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: facebook/wav2vec2-lv-60-espeak-cv-ft
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: wav2vec2-lv-60-espeak-cv-ft-custom_vocab-OtherDiacritics-ds-f1
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # wav2vec2-lv-60-espeak-cv-ft-custom_vocab-OtherDiacritics-ds-f1
16
+
17
+ This model is a fine-tuned version of [facebook/wav2vec2-lv-60-espeak-cv-ft](https://huggingface.co/facebook/wav2vec2-lv-60-espeak-cv-ft) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.2719
20
+ - Per: 0.2780
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 3e-05
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 32
45
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 500
48
+ - num_epochs: 30
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Per |
54
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|
55
+ | 17.3011 | 0.7194 | 400 | 4.6077 | 0.9998 |
56
+ | 4.4327 | 1.4388 | 800 | 4.0875 | 0.9998 |
57
+ | 4.0449 | 2.1583 | 1200 | 3.4625 | 0.9989 |
58
+ | 3.0334 | 2.8777 | 1600 | 1.4123 | 0.4313 |
59
+ | 1.9382 | 3.5971 | 2000 | 0.8080 | 0.3448 |
60
+ | 1.517 | 4.3165 | 2400 | 0.5760 | 0.3209 |
61
+ | 1.3057 | 5.0360 | 2800 | 0.4652 | 0.2986 |
62
+ | 1.1671 | 5.7554 | 3200 | 0.4114 | 0.2926 |
63
+ | 1.0699 | 6.4748 | 3600 | 0.3692 | 0.2905 |
64
+ | 1.0007 | 7.1942 | 4000 | 0.3577 | 0.2870 |
65
+ | 0.9662 | 7.9137 | 4400 | 0.3320 | 0.2866 |
66
+ | 0.9176 | 8.6331 | 4800 | 0.3338 | 0.2863 |
67
+ | 0.8661 | 9.3525 | 5200 | 0.3190 | 0.2845 |
68
+ | 0.8586 | 10.0719 | 5600 | 0.3193 | 0.2844 |
69
+ | 0.8342 | 10.7914 | 6000 | 0.3057 | 0.2828 |
70
+ | 0.847 | 11.5108 | 6400 | 0.3010 | 0.2828 |
71
+ | 0.7874 | 12.2302 | 6800 | 0.2996 | 0.2832 |
72
+ | 0.7767 | 12.9496 | 7200 | 0.3018 | 0.2827 |
73
+ | 0.7571 | 13.6691 | 7600 | 0.2974 | 0.2816 |
74
+ | 0.7601 | 14.3885 | 8000 | 0.2922 | 0.2823 |
75
+ | 0.7451 | 15.1079 | 8400 | 0.2850 | 0.2815 |
76
+ | 0.7262 | 15.8273 | 8800 | 0.2914 | 0.2807 |
77
+ | 0.7306 | 16.5468 | 9200 | 0.2869 | 0.2807 |
78
+ | 0.7104 | 17.2662 | 9600 | 0.2882 | 0.2809 |
79
+ | 0.7057 | 17.9856 | 10000 | 0.2828 | 0.2822 |
80
+ | 0.6814 | 18.7050 | 10400 | 0.2836 | 0.2811 |
81
+ | 0.6706 | 19.4245 | 10800 | 0.2838 | 0.2804 |
82
+ | 0.685 | 20.1439 | 11200 | 0.2764 | 0.2814 |
83
+ | 0.666 | 20.8633 | 11600 | 0.2756 | 0.2805 |
84
+ | 0.6658 | 21.5827 | 12000 | 0.2782 | 0.2805 |
85
+ | 0.6858 | 22.3022 | 12400 | 0.2745 | 0.2793 |
86
+ | 0.6716 | 23.0216 | 12800 | 0.2735 | 0.2773 |
87
+ | 0.6539 | 23.7410 | 13200 | 0.2745 | 0.2798 |
88
+ | 0.6607 | 24.4604 | 13600 | 0.2752 | 0.2789 |
89
+ | 0.6511 | 25.1799 | 14000 | 0.2744 | 0.2794 |
90
+ | 0.6502 | 25.8993 | 14400 | 0.2733 | 0.2786 |
91
+ | 0.633 | 26.6187 | 14800 | 0.2729 | 0.2777 |
92
+ | 0.6439 | 27.3381 | 15200 | 0.2730 | 0.2783 |
93
+ | 0.6206 | 28.0576 | 15600 | 0.2727 | 0.2787 |
94
+ | 0.6456 | 28.7770 | 16000 | 0.2718 | 0.2779 |
95
+ | 0.6273 | 29.4964 | 16400 | 0.2719 | 0.2780 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.57.6
101
+ - Pytorch 2.9.1+cu128
102
+ - Datasets 4.5.0
103
+ - Tokenizers 0.22.2
config.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "adapter_attn_dim": null,
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": 0.1,
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
+ "dtype": "float32",
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.0,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_size": 1024,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 4096,
62
+ "layer_norm_eps": 1e-05,
63
+ "layerdrop": 0.1,
64
+ "mask_channel_length": 10,
65
+ "mask_channel_min_space": 1,
66
+ "mask_channel_other": 0.0,
67
+ "mask_channel_prob": 0.0,
68
+ "mask_channel_selection": "static",
69
+ "mask_feature_length": 10,
70
+ "mask_feature_min_masks": 0,
71
+ "mask_feature_prob": 0.0,
72
+ "mask_time_length": 10,
73
+ "mask_time_min_masks": 2,
74
+ "mask_time_min_space": 1,
75
+ "mask_time_other": 0.0,
76
+ "mask_time_prob": 0.05,
77
+ "mask_time_selection": "static",
78
+ "model_type": "wav2vec2",
79
+ "num_adapter_layers": 3,
80
+ "num_attention_heads": 16,
81
+ "num_codevector_groups": 2,
82
+ "num_codevectors_per_group": 320,
83
+ "num_conv_pos_embedding_groups": 16,
84
+ "num_conv_pos_embeddings": 128,
85
+ "num_feat_extract_layers": 7,
86
+ "num_hidden_layers": 24,
87
+ "num_negatives": 100,
88
+ "output_hidden_size": 1024,
89
+ "pad_token_id": 61,
90
+ "proj_codevector_dim": 768,
91
+ "tdnn_dilation": [
92
+ 1,
93
+ 2,
94
+ 3,
95
+ 1,
96
+ 1
97
+ ],
98
+ "tdnn_dim": [
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 512,
103
+ 1500
104
+ ],
105
+ "tdnn_kernel": [
106
+ 5,
107
+ 3,
108
+ 3,
109
+ 1,
110
+ 1
111
+ ],
112
+ "transformers_version": "4.57.6",
113
+ "use_weighted_layer_sum": false,
114
+ "vocab_size": 64,
115
+ "xvector_output_dim": 512
116
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9130a0edaf11437c8e727c0cc252ebda3a4f9be1072a5eaab0640a18d9db611a
3
+ size 1262069880
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,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
runs/Apr16_20-06-48_Lydia/events.out.tfevents.1776388046.Lydia.22384.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20c993cc50b90417cbfee2bc8949c9c0eeab8004310191e4947dd1bdab6db712
3
+ size 28810
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba5f056cd916597378558760c05b82696fc5332dc9c126944784266557fb5dc7
3
+ size 5905