update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- common_voice_8_0
|
7 |
+
metrics:
|
8 |
+
- wer
|
9 |
+
model-index:
|
10 |
+
- name: wav2vec2-large-xls-r-300m-frisian-cv-8
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Automatic Speech Recognition
|
14 |
+
type: automatic-speech-recognition
|
15 |
+
dataset:
|
16 |
+
name: common_voice_8_0
|
17 |
+
type: common_voice_8_0
|
18 |
+
config: fy-NL
|
19 |
+
split: validation
|
20 |
+
args: fy-NL
|
21 |
+
metrics:
|
22 |
+
- name: Wer
|
23 |
+
type: wer
|
24 |
+
value: 0.07238251678331667
|
25 |
+
---
|
26 |
+
|
27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
28 |
+
should probably proofread and complete it, then remove this comment. -->
|
29 |
+
|
30 |
+
# wav2vec2-large-xls-r-300m-frisian-cv-8
|
31 |
+
|
32 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_8_0 dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.0707
|
35 |
+
- Wer: 0.0724
|
36 |
+
|
37 |
+
## Model description
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Intended uses & limitations
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training and evaluation data
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training procedure
|
50 |
+
|
51 |
+
### Training hyperparameters
|
52 |
+
|
53 |
+
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 5e-05
|
55 |
+
- train_batch_size: 32
|
56 |
+
- eval_batch_size: 8
|
57 |
+
- seed: 42
|
58 |
+
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: linear
|
60 |
+
- lr_scheduler_warmup_ratio: 0.1
|
61 |
+
- num_epochs: 40
|
62 |
+
- mixed_precision_training: Native AMP
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
67 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
68 |
+
| 14.7268 | 0.43 | 400 | 8.7389 | 1.0 |
|
69 |
+
| 5.3377 | 0.86 | 800 | 3.7016 | 1.0 |
|
70 |
+
| 3.343 | 1.29 | 1200 | 3.0984 | 1.0 |
|
71 |
+
| 3.0306 | 1.71 | 1600 | 2.9643 | 1.0 |
|
72 |
+
| 2.9511 | 2.14 | 2000 | 2.9273 | 1.0 |
|
73 |
+
| 2.9078 | 2.57 | 2400 | 2.8202 | 1.0 |
|
74 |
+
| 2.4965 | 3.0 | 2800 | 1.3805 | 0.8888 |
|
75 |
+
| 1.5378 | 3.43 | 3200 | 0.6556 | 0.5720 |
|
76 |
+
| 1.119 | 3.86 | 3600 | 0.4260 | 0.4077 |
|
77 |
+
| 0.9159 | 4.29 | 4000 | 0.3457 | 0.3322 |
|
78 |
+
| 0.8037 | 4.72 | 4400 | 0.2765 | 0.2850 |
|
79 |
+
| 0.7411 | 5.14 | 4800 | 0.2447 | 0.2473 |
|
80 |
+
| 0.6767 | 5.57 | 5200 | 0.2176 | 0.2234 |
|
81 |
+
| 0.6296 | 6.0 | 5600 | 0.1996 | 0.2078 |
|
82 |
+
| 0.6165 | 6.43 | 6000 | 0.1891 | 0.1977 |
|
83 |
+
| 0.5856 | 6.86 | 6400 | 0.1763 | 0.1855 |
|
84 |
+
| 0.5674 | 7.29 | 6800 | 0.1708 | 0.1797 |
|
85 |
+
| 0.5399 | 7.72 | 7200 | 0.1593 | 0.1694 |
|
86 |
+
| 0.5195 | 8.15 | 7600 | 0.1551 | 0.1660 |
|
87 |
+
| 0.4973 | 8.57 | 8000 | 0.1509 | 0.1583 |
|
88 |
+
| 0.4907 | 9.0 | 8400 | 0.1480 | 0.1525 |
|
89 |
+
| 0.4681 | 9.43 | 8800 | 0.1389 | 0.1494 |
|
90 |
+
| 0.4513 | 9.86 | 9200 | 0.1368 | 0.1414 |
|
91 |
+
| 0.4486 | 10.29 | 9600 | 0.1294 | 0.1390 |
|
92 |
+
| 0.4381 | 10.72 | 10000 | 0.1262 | 0.1354 |
|
93 |
+
| 0.443 | 11.15 | 10400 | 0.1234 | 0.1313 |
|
94 |
+
| 0.4182 | 11.58 | 10800 | 0.1196 | 0.1294 |
|
95 |
+
| 0.4036 | 12.0 | 11200 | 0.1194 | 0.1259 |
|
96 |
+
| 0.4027 | 12.43 | 11600 | 0.1170 | 0.1226 |
|
97 |
+
| 0.4066 | 12.86 | 12000 | 0.1156 | 0.1224 |
|
98 |
+
| 0.3885 | 13.29 | 12400 | 0.1136 | 0.1174 |
|
99 |
+
| 0.3859 | 13.72 | 12800 | 0.1121 | 0.1146 |
|
100 |
+
| 0.3812 | 14.15 | 13200 | 0.1097 | 0.1141 |
|
101 |
+
| 0.3774 | 14.58 | 13600 | 0.1059 | 0.1130 |
|
102 |
+
| 0.3678 | 15.01 | 14000 | 0.1058 | 0.1096 |
|
103 |
+
| 0.3586 | 15.43 | 14400 | 0.1026 | 0.1099 |
|
104 |
+
| 0.3612 | 15.86 | 14800 | 0.1010 | 0.1076 |
|
105 |
+
| 0.3626 | 16.29 | 15200 | 0.0993 | 0.1068 |
|
106 |
+
| 0.353 | 16.72 | 15600 | 0.0974 | 0.1046 |
|
107 |
+
| 0.3564 | 17.15 | 16000 | 0.0986 | 0.1037 |
|
108 |
+
| 0.3447 | 17.58 | 16400 | 0.0977 | 0.1041 |
|
109 |
+
| 0.3454 | 18.01 | 16800 | 0.0945 | 0.1023 |
|
110 |
+
| 0.3338 | 18.44 | 17200 | 0.0904 | 0.0996 |
|
111 |
+
| 0.3359 | 18.86 | 17600 | 0.0950 | 0.1002 |
|
112 |
+
| 0.3179 | 19.29 | 18000 | 0.0911 | 0.0977 |
|
113 |
+
| 0.3202 | 19.72 | 18400 | 0.0906 | 0.0979 |
|
114 |
+
| 0.3317 | 20.15 | 18800 | 0.0894 | 0.0963 |
|
115 |
+
| 0.3187 | 20.58 | 19200 | 0.0878 | 0.0938 |
|
116 |
+
| 0.3075 | 21.01 | 19600 | 0.0893 | 0.0937 |
|
117 |
+
| 0.3032 | 21.44 | 20000 | 0.0872 | 0.0923 |
|
118 |
+
| 0.3048 | 21.86 | 20400 | 0.0848 | 0.0921 |
|
119 |
+
| 0.3045 | 22.29 | 20800 | 0.0860 | 0.0887 |
|
120 |
+
| 0.316 | 22.72 | 21200 | 0.0841 | 0.0896 |
|
121 |
+
| 0.2986 | 23.15 | 21600 | 0.0840 | 0.0876 |
|
122 |
+
| 0.294 | 23.58 | 22000 | 0.0824 | 0.0862 |
|
123 |
+
| 0.313 | 24.01 | 22400 | 0.0814 | 0.0855 |
|
124 |
+
| 0.2864 | 24.44 | 22800 | 0.0816 | 0.0861 |
|
125 |
+
| 0.2927 | 24.87 | 23200 | 0.0807 | 0.0875 |
|
126 |
+
| 0.294 | 25.29 | 23600 | 0.0829 | 0.0826 |
|
127 |
+
| 0.2834 | 25.72 | 24000 | 0.0794 | 0.0823 |
|
128 |
+
| 0.2852 | 26.15 | 24400 | 0.0781 | 0.0815 |
|
129 |
+
| 0.2823 | 26.58 | 24800 | 0.0781 | 0.0821 |
|
130 |
+
| 0.2835 | 27.01 | 25200 | 0.0788 | 0.0826 |
|
131 |
+
| 0.2763 | 27.44 | 25600 | 0.0789 | 0.0823 |
|
132 |
+
| 0.2845 | 27.87 | 26000 | 0.0767 | 0.0803 |
|
133 |
+
| 0.2777 | 28.3 | 26400 | 0.0775 | 0.0809 |
|
134 |
+
| 0.275 | 28.72 | 26800 | 0.0758 | 0.0794 |
|
135 |
+
| 0.2707 | 29.15 | 27200 | 0.0745 | 0.0790 |
|
136 |
+
| 0.2734 | 29.58 | 27600 | 0.0765 | 0.0797 |
|
137 |
+
| 0.2716 | 30.01 | 28000 | 0.0746 | 0.0780 |
|
138 |
+
| 0.2626 | 30.44 | 28400 | 0.0756 | 0.0776 |
|
139 |
+
| 0.2671 | 30.87 | 28800 | 0.0742 | 0.0763 |
|
140 |
+
| 0.2592 | 31.3 | 29200 | 0.0730 | 0.0771 |
|
141 |
+
| 0.2685 | 31.73 | 29600 | 0.0733 | 0.0760 |
|
142 |
+
| 0.2727 | 32.15 | 30000 | 0.0738 | 0.0758 |
|
143 |
+
| 0.2564 | 32.58 | 30400 | 0.0731 | 0.0763 |
|
144 |
+
| 0.2528 | 33.01 | 30800 | 0.0730 | 0.0758 |
|
145 |
+
| 0.2573 | 33.44 | 31200 | 0.0717 | 0.0746 |
|
146 |
+
| 0.2597 | 33.87 | 31600 | 0.0718 | 0.0760 |
|
147 |
+
| 0.2511 | 34.3 | 32000 | 0.0737 | 0.0750 |
|
148 |
+
| 0.2551 | 34.73 | 32400 | 0.0732 | 0.0758 |
|
149 |
+
| 0.26 | 35.16 | 32800 | 0.0724 | 0.0746 |
|
150 |
+
| 0.2563 | 35.58 | 33200 | 0.0717 | 0.0730 |
|
151 |
+
| 0.2559 | 36.01 | 33600 | 0.0707 | 0.0734 |
|
152 |
+
| 0.2499 | 36.44 | 34000 | 0.0721 | 0.0729 |
|
153 |
+
| 0.252 | 36.87 | 34400 | 0.0716 | 0.0723 |
|
154 |
+
| 0.2448 | 37.3 | 34800 | 0.0711 | 0.0725 |
|
155 |
+
| 0.248 | 37.73 | 35200 | 0.0710 | 0.0727 |
|
156 |
+
| 0.2568 | 38.16 | 35600 | 0.0710 | 0.0720 |
|
157 |
+
| 0.2471 | 38.59 | 36000 | 0.0707 | 0.0725 |
|
158 |
+
| 0.2464 | 39.01 | 36400 | 0.0705 | 0.0719 |
|
159 |
+
| 0.2477 | 39.44 | 36800 | 0.0706 | 0.0727 |
|
160 |
+
| 0.2482 | 39.87 | 37200 | 0.0707 | 0.0724 |
|
161 |
+
|
162 |
+
|
163 |
+
### Framework versions
|
164 |
+
|
165 |
+
- Transformers 4.28.1
|
166 |
+
- Pytorch 2.0.0+cu117
|
167 |
+
- Datasets 2.11.0
|
168 |
+
- Tokenizers 0.13.3
|