Hugging Face's logo

tuanio
/
md_d_l2_arctic

Transformers
Safetensors
wavlm
Generated from Trainer
Inference Endpoints
Model card Files Community
tuanio commited on
Commit
a1597f8
·
verified ·
1 Parent(s): bb24241

Model save

Browse files
Files changed (2) hide show
  1. README.md +141 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/wavlm-base
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - wer
7
+ model-index:
8
+ - name: md_d_l2_arctic
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
+ # md_d_l2_arctic
16
+
17
+ This model is a fine-tuned version of [microsoft/wavlm-base](https://huggingface.co/microsoft/wavlm-base) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.8258
20
+ - Wer: 0.6289
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: 2e-05
40
+ - train_batch_size: 20
41
+ - eval_batch_size: 20
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 40
45
+ - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_ratio: 0.1
48
+ - num_epochs: 100
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
55
+ | 14.3657 | 1.27 | 100 | 9.1210 | 2.4375 |
56
+ | 4.382 | 2.53 | 200 | 3.4219 | 1.0 |
57
+ | 3.2514 | 3.8 | 300 | 2.7881 | 0.9980 |
58
+ | 2.4508 | 5.06 | 400 | 1.8000 | 0.7380 |
59
+ | 1.6168 | 6.33 | 500 | 1.1315 | 0.9678 |
60
+ | 1.1212 | 7.59 | 600 | 0.8749 | 1.0658 |
61
+ | 0.8953 | 8.86 | 700 | 0.7655 | 0.9655 |
62
+ | 0.7684 | 10.13 | 800 | 0.6687 | 0.7621 |
63
+ | 0.6661 | 11.39 | 900 | 0.6319 | 0.6756 |
64
+ | 0.6306 | 12.66 | 1000 | 0.6196 | 0.6963 |
65
+ | 0.5759 | 13.92 | 1100 | 0.5875 | 0.5965 |
66
+ | 0.5417 | 15.19 | 1200 | 0.5780 | 0.6528 |
67
+ | 0.528 | 16.46 | 1300 | 0.5798 | 0.6539 |
68
+ | 0.4857 | 17.72 | 1400 | 0.5569 | 0.5725 |
69
+ | 0.4655 | 18.99 | 1500 | 0.5500 | 0.5755 |
70
+ | 0.4526 | 20.25 | 1600 | 0.5583 | 0.5776 |
71
+ | 0.4287 | 21.52 | 1700 | 0.5557 | 0.5610 |
72
+ | 0.4149 | 22.78 | 1800 | 0.5575 | 0.5748 |
73
+ | 0.3983 | 24.05 | 1900 | 0.5649 | 0.6003 |
74
+ | 0.4001 | 25.32 | 2000 | 0.5674 | 0.5976 |
75
+ | 0.3649 | 26.58 | 2100 | 0.5797 | 0.5805 |
76
+ | 0.3711 | 27.85 | 2200 | 0.5839 | 0.6546 |
77
+ | 0.3547 | 29.11 | 2300 | 0.5735 | 0.5904 |
78
+ | 0.3402 | 30.38 | 2400 | 0.5699 | 0.5426 |
79
+ | 0.3414 | 31.65 | 2500 | 0.5700 | 0.5421 |
80
+ | 0.3255 | 32.91 | 2600 | 0.5745 | 0.5663 |
81
+ | 0.3093 | 34.18 | 2700 | 0.5958 | 0.5932 |
82
+ | 0.315 | 35.44 | 2800 | 0.5934 | 0.5906 |
83
+ | 0.31 | 36.71 | 2900 | 0.6072 | 0.6011 |
84
+ | 0.3026 | 37.97 | 3000 | 0.6038 | 0.5760 |
85
+ | 0.2802 | 39.24 | 3100 | 0.6080 | 0.5777 |
86
+ | 0.2835 | 40.51 | 3200 | 0.6062 | 0.5744 |
87
+ | 0.2585 | 41.77 | 3300 | 0.6225 | 0.5784 |
88
+ | 0.2699 | 43.04 | 3400 | 0.6226 | 0.5665 |
89
+ | 0.2785 | 44.3 | 3500 | 0.6240 | 0.5714 |
90
+ | 0.2689 | 45.57 | 3600 | 0.6295 | 0.5649 |
91
+ | 0.2514 | 46.84 | 3700 | 0.6425 | 0.5421 |
92
+ | 0.2433 | 48.1 | 3800 | 0.6668 | 0.6068 |
93
+ | 0.2403 | 49.37 | 3900 | 0.6563 | 0.5750 |
94
+ | 0.2287 | 50.63 | 4000 | 0.6696 | 0.5933 |
95
+ | 0.2366 | 51.9 | 4100 | 0.6739 | 0.5731 |
96
+ | 0.2295 | 53.16 | 4200 | 0.6809 | 0.6091 |
97
+ | 0.2274 | 54.43 | 4300 | 0.6875 | 0.5914 |
98
+ | 0.2178 | 55.7 | 4400 | 0.6899 | 0.5949 |
99
+ | 0.2176 | 56.96 | 4500 | 0.6925 | 0.5828 |
100
+ | 0.2064 | 58.23 | 4600 | 0.7009 | 0.5985 |
101
+ | 0.2081 | 59.49 | 4700 | 0.7013 | 0.5996 |
102
+ | 0.2093 | 60.76 | 4800 | 0.7257 | 0.6086 |
103
+ | 0.2024 | 62.03 | 4900 | 0.7215 | 0.6003 |
104
+ | 0.1999 | 63.29 | 5000 | 0.7333 | 0.6091 |
105
+ | 0.2064 | 64.56 | 5100 | 0.7530 | 0.6397 |
106
+ | 0.186 | 65.82 | 5200 | 0.7542 | 0.6349 |
107
+ | 0.186 | 67.09 | 5300 | 0.7416 | 0.6270 |
108
+ | 0.1807 | 68.35 | 5400 | 0.7549 | 0.6352 |
109
+ | 0.1784 | 69.62 | 5500 | 0.7506 | 0.5844 |
110
+ | 0.1824 | 70.89 | 5600 | 0.7611 | 0.6253 |
111
+ | 0.1769 | 72.15 | 5700 | 0.7713 | 0.5927 |
112
+ | 0.1843 | 73.42 | 5800 | 0.7720 | 0.5956 |
113
+ | 0.1709 | 74.68 | 5900 | 0.7805 | 0.6258 |
114
+ | 0.1691 | 75.95 | 6000 | 0.7865 | 0.6282 |
115
+ | 0.1701 | 77.22 | 6100 | 0.7808 | 0.6218 |
116
+ | 0.1735 | 78.48 | 6200 | 0.7790 | 0.5966 |
117
+ | 0.1746 | 79.75 | 6300 | 0.7949 | 0.6431 |
118
+ | 0.1745 | 81.01 | 6400 | 0.8126 | 0.6285 |
119
+ | 0.1605 | 82.28 | 6500 | 0.8113 | 0.6195 |
120
+ | 0.1579 | 83.54 | 6600 | 0.7977 | 0.6155 |
121
+ | 0.1704 | 84.81 | 6700 | 0.8017 | 0.6140 |
122
+ | 0.1659 | 86.08 | 6800 | 0.8147 | 0.6279 |
123
+ | 0.166 | 87.34 | 6900 | 0.8088 | 0.6350 |
124
+ | 0.1539 | 88.61 | 7000 | 0.8053 | 0.6164 |
125
+ | 0.1589 | 89.87 | 7100 | 0.8189 | 0.6357 |
126
+ | 0.1559 | 91.14 | 7200 | 0.8152 | 0.6258 |
127
+ | 0.1564 | 92.41 | 7300 | 0.8191 | 0.6245 |
128
+ | 0.158 | 93.67 | 7400 | 0.8255 | 0.6333 |
129
+ | 0.1595 | 94.94 | 7500 | 0.8184 | 0.6206 |
130
+ | 0.1638 | 96.2 | 7600 | 0.8230 | 0.6364 |
131
+ | 0.1629 | 97.47 | 7700 | 0.8245 | 0.6312 |
132
+ | 0.1531 | 98.73 | 7800 | 0.8226 | 0.6267 |
133
+ | 0.1572 | 100.0 | 7900 | 0.8258 | 0.6289 |
134
+
135
+
136
+ ### Framework versions
137
+
138
+ - Transformers 4.39.3
139
+ - Pytorch 2.1.2
140
+ - Datasets 2.18.0
141
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db561c2d4ca669d24103f8d5f0e14fd0fb3ec309e127e5a2ae65a28884af9c0a
3
  size 772527092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bcd2b80dc0405872c7d187abdbce061861e681da027b67f2f2ddb5c8fbddd66
3
  size 772527092