Hugging Face's logo

Finnish-NLP
/
wav2vec2-large-uralic-voxpopuli-v2-finnish

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Finnish
wav2vec2
finnish
Generated from Trainer
hf-asr-leaderboard
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
aapot commited on
Commit
fff5d98
·
1 Parent(s): 4d4f599

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +118 -0
README.md ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: wav2vec2-large-uralic-voxpopuli-v2-finnish
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
+ # wav2vec2-large-uralic-voxpopuli-v2-finnish
14
+
15
+ This model is a fine-tuned version of [facebook/wav2vec2-large-uralic-voxpopuli-v2](https://huggingface.co/facebook/wav2vec2-large-uralic-voxpopuli-v2) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.0828
18
+ - Wer: 0.1075
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: 32
39
+ - eval_batch_size: 32
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - lr_scheduler_warmup_steps: 500
44
+ - num_epochs: 10
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
50
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
51
+ | 1.9421 | 0.17 | 500 | 0.8633 | 0.8870 |
52
+ | 0.572 | 0.33 | 1000 | 0.1650 | 0.1829 |
53
+ | 0.5149 | 0.5 | 1500 | 0.1416 | 0.1711 |
54
+ | 0.4884 | 0.66 | 2000 | 0.1265 | 0.1605 |
55
+ | 0.4729 | 0.83 | 2500 | 0.1205 | 0.1485 |
56
+ | 0.4723 | 1.0 | 3000 | 0.1108 | 0.1403 |
57
+ | 0.443 | 1.16 | 3500 | 0.1175 | 0.1439 |
58
+ | 0.4378 | 1.33 | 4000 | 0.1083 | 0.1482 |
59
+ | 0.4313 | 1.49 | 4500 | 0.1110 | 0.1398 |
60
+ | 0.4182 | 1.66 | 5000 | 0.1024 | 0.1418 |
61
+ | 0.3884 | 1.83 | 5500 | 0.1032 | 0.1395 |
62
+ | 0.4034 | 1.99 | 6000 | 0.0985 | 0.1318 |
63
+ | 0.3735 | 2.16 | 6500 | 0.1008 | 0.1355 |
64
+ | 0.4174 | 2.32 | 7000 | 0.0970 | 0.1361 |
65
+ | 0.3581 | 2.49 | 7500 | 0.0968 | 0.1297 |
66
+ | 0.3783 | 2.66 | 8000 | 0.0881 | 0.1284 |
67
+ | 0.3827 | 2.82 | 8500 | 0.0921 | 0.1352 |
68
+ | 0.3651 | 2.99 | 9000 | 0.0861 | 0.1298 |
69
+ | 0.3684 | 3.15 | 9500 | 0.0844 | 0.1270 |
70
+ | 0.3784 | 3.32 | 10000 | 0.0870 | 0.1248 |
71
+ | 0.356 | 3.48 | 10500 | 0.0828 | 0.1214 |
72
+ | 0.3524 | 3.65 | 11000 | 0.0878 | 0.1218 |
73
+ | 0.3879 | 3.82 | 11500 | 0.0874 | 0.1216 |
74
+ | 0.3521 | 3.98 | 12000 | 0.0860 | 0.1210 |
75
+ | 0.3527 | 4.15 | 12500 | 0.0818 | 0.1184 |
76
+ | 0.3529 | 4.31 | 13000 | 0.0787 | 0.1185 |
77
+ | 0.3114 | 4.48 | 13500 | 0.0852 | 0.1202 |
78
+ | 0.3495 | 4.65 | 14000 | 0.0807 | 0.1187 |
79
+ | 0.34 | 4.81 | 14500 | 0.0796 | 0.1162 |
80
+ | 0.3646 | 4.98 | 15000 | 0.0782 | 0.1149 |
81
+ | 0.3004 | 5.14 | 15500 | 0.0799 | 0.1142 |
82
+ | 0.3167 | 5.31 | 16000 | 0.0847 | 0.1123 |
83
+ | 0.3249 | 5.48 | 16500 | 0.0837 | 0.1171 |
84
+ | 0.3202 | 5.64 | 17000 | 0.0749 | 0.1109 |
85
+ | 0.3104 | 5.81 | 17500 | 0.0798 | 0.1093 |
86
+ | 0.3039 | 5.97 | 18000 | 0.0810 | 0.1132 |
87
+ | 0.3157 | 6.14 | 18500 | 0.0847 | 0.1156 |
88
+ | 0.3133 | 6.31 | 19000 | 0.0833 | 0.1140 |
89
+ | 0.3203 | 6.47 | 19500 | 0.0838 | 0.1113 |
90
+ | 0.3178 | 6.64 | 20000 | 0.0907 | 0.1141 |
91
+ | 0.3182 | 6.8 | 20500 | 0.0938 | 0.1143 |
92
+ | 0.3 | 6.97 | 21000 | 0.0854 | 0.1133 |
93
+ | 0.3151 | 7.14 | 21500 | 0.0859 | 0.1109 |
94
+ | 0.2963 | 7.3 | 22000 | 0.0832 | 0.1122 |
95
+ | 0.3099 | 7.47 | 22500 | 0.0865 | 0.1103 |
96
+ | 0.322 | 7.63 | 23000 | 0.0833 | 0.1105 |
97
+ | 0.3064 | 7.8 | 23500 | 0.0865 | 0.1078 |
98
+ | 0.2964 | 7.97 | 24000 | 0.0859 | 0.1096 |
99
+ | 0.2869 | 8.13 | 24500 | 0.0872 | 0.1100 |
100
+ | 0.315 | 8.3 | 25000 | 0.0869 | 0.1099 |
101
+ | 0.3003 | 8.46 | 25500 | 0.0878 | 0.1105 |
102
+ | 0.2947 | 8.63 | 26000 | 0.0884 | 0.1084 |
103
+ | 0.297 | 8.8 | 26500 | 0.0891 | 0.1102 |
104
+ | 0.3049 | 8.96 | 27000 | 0.0863 | 0.1081 |
105
+ | 0.2957 | 9.13 | 27500 | 0.0846 | 0.1083 |
106
+ | 0.2908 | 9.29 | 28000 | 0.0848 | 0.1059 |
107
+ | 0.2955 | 9.46 | 28500 | 0.0846 | 0.1085 |
108
+ | 0.2991 | 9.62 | 29000 | 0.0839 | 0.1081 |
109
+ | 0.3112 | 9.79 | 29500 | 0.0832 | 0.1071 |
110
+ | 0.29 | 9.96 | 30000 | 0.0828 | 0.1075 |
111
+
112
+
113
+ ### Framework versions
114
+
115
+ - Transformers 4.19.2
116
+ - Pytorch 1.11.0+cu102
117
+ - Datasets 2.2.2
118
+ - Tokenizers 0.11.0