Hugging Face's logo

niclas
/
model_en

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Model card Files
xet
Community
niclas commited on
Commit
41e527a
·
1 Parent(s): 2436fcd

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +124 -0
README.md ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: model_en
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # model_en
14
+
15
+ This model is a fine-tuned version of [facebook/wav2vec2-large](https://huggingface.co/facebook/wav2vec2-large) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 1.8610
18
+ - Wer: 0.2641
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0001
38
+ - train_batch_size: 4
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 2
42
+ - total_train_batch_size: 8
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 1000
46
+ - num_epochs: 200
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
51
+ |:-------------:|:------:|:-----:|:---------------:|:------:|
52
+ | 6.3443 | 3.05 | 250 | 3.0966 | 1.0 |
53
+ | 2.9847 | 6.1 | 500 | 3.0603 | 1.0 |
54
+ | 2.9263 | 9.15 | 750 | 2.9131 | 1.0 |
55
+ | 2.2584 | 12.19 | 1000 | 1.4318 | 0.6575 |
56
+ | 1.2603 | 15.24 | 1250 | 1.1964 | 0.4994 |
57
+ | 0.9182 | 18.29 | 1500 | 1.1494 | 0.4485 |
58
+ | 0.7462 | 21.34 | 1750 | 1.2171 | 0.4357 |
59
+ | 0.6129 | 24.39 | 2000 | 1.0557 | 0.3468 |
60
+ | 0.5364 | 27.44 | 2250 | 1.1069 | 0.4222 |
61
+ | 0.4607 | 30.48 | 2500 | 1.3270 | 0.3370 |
62
+ | 0.4139 | 33.53 | 2750 | 1.1814 | 0.3658 |
63
+ | 0.3587 | 36.58 | 3000 | 1.2423 | 0.3419 |
64
+ | 0.321 | 39.63 | 3250 | 1.2931 | 0.3211 |
65
+ | 0.2961 | 42.68 | 3500 | 1.1409 | 0.3315 |
66
+ | 0.2635 | 45.73 | 3750 | 1.4537 | 0.3241 |
67
+ | 0.2498 | 48.78 | 4000 | 1.2643 | 0.3192 |
68
+ | 0.2352 | 51.82 | 4250 | 1.2789 | 0.3278 |
69
+ | 0.2193 | 54.87 | 4500 | 1.4220 | 0.3021 |
70
+ | 0.2068 | 57.92 | 4750 | 1.3567 | 0.3713 |
71
+ | 0.2055 | 60.97 | 5000 | 1.5375 | 0.3051 |
72
+ | 0.198 | 64.02 | 5250 | 1.2676 | 0.2782 |
73
+ | 0.1835 | 67.07 | 5500 | 1.3905 | 0.2825 |
74
+ | 0.1655 | 70.12 | 5750 | 1.7000 | 0.2978 |
75
+ | 0.1677 | 73.17 | 6000 | 1.4250 | 0.2812 |
76
+ | 0.1522 | 76.22 | 6250 | 1.4220 | 0.2941 |
77
+ | 0.1522 | 79.27 | 6500 | 1.5195 | 0.3021 |
78
+ | 0.1344 | 82.32 | 6750 | 1.3749 | 0.2996 |
79
+ | 0.1298 | 85.36 | 7000 | 1.6663 | 0.2849 |
80
+ | 0.1293 | 88.41 | 7250 | 1.4564 | 0.2892 |
81
+ | 0.1264 | 91.46 | 7500 | 1.4373 | 0.2935 |
82
+ | 0.1243 | 94.51 | 7750 | 1.6572 | 0.2972 |
83
+ | 0.1141 | 97.56 | 8000 | 1.4936 | 0.2892 |
84
+ | 0.1086 | 100.61 | 8250 | 1.5231 | 0.2868 |
85
+ | 0.1056 | 103.65 | 8500 | 1.3733 | 0.2763 |
86
+ | 0.098 | 106.7 | 8750 | 1.4887 | 0.2923 |
87
+ | 0.0984 | 109.75 | 9000 | 1.3779 | 0.2923 |
88
+ | 0.0916 | 112.8 | 9250 | 1.4868 | 0.2604 |
89
+ | 0.0881 | 115.85 | 9500 | 1.7991 | 0.2996 |
90
+ | 0.0846 | 118.9 | 9750 | 1.5845 | 0.2849 |
91
+ | 0.0861 | 121.95 | 10000 | 1.6684 | 0.2794 |
92
+ | 0.0806 | 124.99 | 10250 | 1.5774 | 0.3039 |
93
+ | 0.0822 | 128.05 | 10500 | 1.5928 | 0.2886 |
94
+ | 0.0788 | 131.1 | 10750 | 1.6158 | 0.2880 |
95
+ | 0.0704 | 134.15 | 11000 | 1.7679 | 0.2941 |
96
+ | 0.0721 | 137.19 | 11250 | 1.7055 | 0.2629 |
97
+ | 0.0723 | 140.24 | 11500 | 1.5473 | 0.2653 |
98
+ | 0.0676 | 143.29 | 11750 | 1.8963 | 0.2745 |
99
+ | 0.0665 | 146.34 | 12000 | 1.6367 | 0.2739 |
100
+ | 0.0618 | 149.39 | 12250 | 1.6757 | 0.2745 |
101
+ | 0.0595 | 152.44 | 12500 | 1.5900 | 0.2745 |
102
+ | 0.056 | 155.48 | 12750 | 1.5362 | 0.2794 |
103
+ | 0.0587 | 158.53 | 13000 | 1.4616 | 0.2684 |
104
+ | 0.0519 | 161.58 | 13250 | 1.6867 | 0.2549 |
105
+ | 0.0569 | 164.63 | 13500 | 1.8294 | 0.2574 |
106
+ | 0.0497 | 167.68 | 13750 | 1.7844 | 0.2868 |
107
+ | 0.0531 | 170.73 | 14000 | 1.7564 | 0.2770 |
108
+ | 0.0489 | 173.78 | 14250 | 1.5811 | 0.2629 |
109
+ | 0.0524 | 176.82 | 14500 | 1.6925 | 0.2684 |
110
+ | 0.0431 | 179.87 | 14750 | 1.7236 | 0.2653 |
111
+ | 0.0457 | 182.92 | 15000 | 1.7460 | 0.2512 |
112
+ | 0.045 | 185.97 | 15250 | 1.8096 | 0.2610 |
113
+ | 0.0402 | 189.02 | 15500 | 1.8795 | 0.2635 |
114
+ | 0.0529 | 192.07 | 15750 | 1.8310 | 0.2616 |
115
+ | 0.0396 | 195.12 | 16000 | 1.8380 | 0.2635 |
116
+ | 0.0432 | 198.17 | 16250 | 1.8610 | 0.2641 |
117
+
118
+
119
+ ### Framework versions
120
+
121
+ - Transformers 4.11.3
122
+ - Pytorch 1.9.0
123
+ - Datasets 1.13.3
124
+ - Tokenizers 0.10.3