Hugging Face's logo

aapot
/
wav2vec2-xlsr-1b-finnish-v2

Automatic Speech Recognition
Transformers
PyTorch
Finnish
wav2vec2
finnish
generated_from_trainer
hf-asr-leaderboard
robust-speech-event
Eval Results
Inference Endpoints
Model card Files Community
aapot commited on
Commit
55ac454
•
1 Parent(s): 65d09f1

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +117 -0
README.md ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: wav2vec2-xlsr-1b-finnish-v2
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-xlsr-1b-finnish-v2
14
+
15
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.0737
18
+ - Wer: 0.0975
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: 5e-05
38
+ - train_batch_size: 32
39
+ - eval_batch_size: 8
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
+ | 0.7778 | 0.17 | 500 | 0.2851 | 0.3572 |
52
+ | 0.5506 | 0.34 | 1000 | 0.1595 | 0.2130 |
53
+ | 0.6569 | 0.5 | 1500 | 0.1458 | 0.2046 |
54
+ | 0.5997 | 0.67 | 2000 | 0.1374 | 0.1975 |
55
+ | 0.542 | 0.84 | 2500 | 0.1390 | 0.1956 |
56
+ | 0.4815 | 1.01 | 3000 | 0.1266 | 0.1813 |
57
+ | 0.6982 | 1.17 | 3500 | 0.1441 | 0.1965 |
58
+ | 0.4522 | 1.34 | 4000 | 0.1232 | 0.1822 |
59
+ | 0.4655 | 1.51 | 4500 | 0.1209 | 0.1702 |
60
+ | 0.4069 | 1.68 | 5000 | 0.1149 | 0.1688 |
61
+ | 0.4226 | 1.84 | 5500 | 0.1121 | 0.1560 |
62
+ | 0.3993 | 2.01 | 6000 | 0.1091 | 0.1557 |
63
+ | 0.406 | 2.18 | 6500 | 0.1115 | 0.1553 |
64
+ | 0.4098 | 2.35 | 7000 | 0.1144 | 0.1560 |
65
+ | 0.3995 | 2.51 | 7500 | 0.1028 | 0.1476 |
66
+ | 0.4101 | 2.68 | 8000 | 0.1129 | 0.1511 |
67
+ | 0.3636 | 2.85 | 8500 | 0.1025 | 0.1517 |
68
+ | 0.3534 | 3.02 | 9000 | 0.1068 | 0.1480 |
69
+ | 0.3836 | 3.18 | 9500 | 0.1072 | 0.1459 |
70
+ | 0.3531 | 3.35 | 10000 | 0.0928 | 0.1367 |
71
+ | 0.3649 | 3.52 | 10500 | 0.1042 | 0.1426 |
72
+ | 0.3645 | 3.69 | 11000 | 0.0979 | 0.1433 |
73
+ | 0.3685 | 3.85 | 11500 | 0.0947 | 0.1346 |
74
+ | 0.3325 | 4.02 | 12000 | 0.0991 | 0.1352 |
75
+ | 0.3497 | 4.19 | 12500 | 0.0919 | 0.1358 |
76
+ | 0.3303 | 4.36 | 13000 | 0.0888 | 0.1272 |
77
+ | 0.3323 | 4.52 | 13500 | 0.0888 | 0.1277 |
78
+ | 0.3452 | 4.69 | 14000 | 0.0894 | 0.1279 |
79
+ | 0.337 | 4.86 | 14500 | 0.0917 | 0.1289 |
80
+ | 0.3114 | 5.03 | 15000 | 0.0942 | 0.1313 |
81
+ | 0.3099 | 5.19 | 15500 | 0.0902 | 0.1239 |
82
+ | 0.3079 | 5.36 | 16000 | 0.0871 | 0.1256 |
83
+ | 0.3293 | 5.53 | 16500 | 0.0861 | 0.1263 |
84
+ | 0.3123 | 5.7 | 17000 | 0.0876 | 0.1203 |
85
+ | 0.3093 | 5.86 | 17500 | 0.0848 | 0.1226 |
86
+ | 0.2903 | 6.03 | 18000 | 0.0914 | 0.1221 |
87
+ | 0.297 | 6.2 | 18500 | 0.0841 | 0.1185 |
88
+ | 0.2797 | 6.37 | 19000 | 0.0858 | 0.1165 |
89
+ | 0.2878 | 6.53 | 19500 | 0.0874 | 0.1161 |
90
+ | 0.2974 | 6.7 | 20000 | 0.0835 | 0.1173 |
91
+ | 0.3051 | 6.87 | 20500 | 0.0835 | 0.1178 |
92
+ | 0.2941 | 7.04 | 21000 | 0.0852 | 0.1155 |
93
+ | 0.258 | 7.21 | 21500 | 0.0832 | 0.1132 |
94
+ | 0.2778 | 7.37 | 22000 | 0.0829 | 0.1110 |
95
+ | 0.2751 | 7.54 | 22500 | 0.0822 | 0.1069 |
96
+ | 0.2887 | 7.71 | 23000 | 0.0819 | 0.1103 |
97
+ | 0.2509 | 7.88 | 23500 | 0.0787 | 0.1055 |
98
+ | 0.2501 | 8.04 | 24000 | 0.0807 | 0.1076 |
99
+ | 0.2399 | 8.21 | 24500 | 0.0784 | 0.1052 |
100
+ | 0.2539 | 8.38 | 25000 | 0.0772 | 0.1075 |
101
+ | 0.248 | 8.55 | 25500 | 0.0772 | 0.1055 |
102
+ | 0.2689 | 8.71 | 26000 | 0.0763 | 0.1027 |
103
+ | 0.2855 | 8.88 | 26500 | 0.0756 | 0.1035 |
104
+ | 0.2421 | 9.05 | 27000 | 0.0771 | 0.0998 |
105
+ | 0.2497 | 9.22 | 27500 | 0.0756 | 0.0971 |
106
+ | 0.2367 | 9.38 | 28000 | 0.0741 | 0.0974 |
107
+ | 0.2473 | 9.55 | 28500 | 0.0739 | 0.0982 |
108
+ | 0.2396 | 9.72 | 29000 | 0.0756 | 0.0991 |
109
+ | 0.2602 | 9.89 | 29500 | 0.0737 | 0.0975 |
110
+
111
+
112
+ ### Framework versions
113
+
114
+ - Transformers 4.17.0.dev0
115
+ - Pytorch 1.10.2+cu102
116
+ - Datasets 1.18.3
117
+ - Tokenizers 0.11.0