🚀 Ascend
This model is a fine - tuned version of GleamEyeBeast/ascend on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3718
- Wer: 0.6412
- Cer: 0.2428
🚀 Quick Start
This section provides an overview of the Ascend model and its evaluation results. The model is fine - tuned from GleamEyeBeast/ascend on an unknown dataset, and shows specific performance metrics on the evaluation set.
📚 Documentation
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e - 05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
Wer |
Cer |
| 0.5769 |
1.0 |
688 |
1.1864 |
0.7716 |
0.3159 |
| 0.5215 |
2.0 |
1376 |
1.1613 |
0.7504 |
0.2965 |
| 0.4188 |
3.0 |
2064 |
1.1644 |
0.7389 |
0.2950 |
| 0.3695 |
4.0 |
2752 |
1.1937 |
0.7184 |
0.2815 |
| 0.3404 |
5.0 |
3440 |
1.1947 |
0.7083 |
0.2719 |
| 0.2885 |
6.0 |
4128 |
1.2314 |
0.7108 |
0.2685 |
| 0.2727 |
7.0 |
4816 |
1.2243 |
0.6850 |
0.2616 |
| 0.2417 |
8.0 |
5504 |
1.2506 |
0.6767 |
0.2608 |
| 0.2207 |
9.0 |
6192 |
1.2804 |
0.6922 |
0.2595 |
| 0.2195 |
10.0 |
6880 |
1.2582 |
0.6818 |
0.2575 |
| 0.1896 |
11.0 |
7568 |
1.3101 |
0.6814 |
0.2545 |
| 0.1961 |
12.0 |
8256 |
1.2793 |
0.6706 |
0.2526 |
| 0.1752 |
13.0 |
8944 |
1.2643 |
0.6584 |
0.2509 |
| 0.1638 |
14.0 |
9632 |
1.3152 |
0.6588 |
0.2482 |
| 0.1522 |
15.0 |
10320 |
1.3098 |
0.6433 |
0.2439 |
| 0.1351 |
16.0 |
11008 |
1.3253 |
0.6537 |
0.2447 |
| 0.1266 |
17.0 |
11696 |
1.3394 |
0.6365 |
0.2418 |
| 0.1289 |
18.0 |
12384 |
1.3718 |
0.6412 |
0.2443 |
| 0.1204 |
19.0 |
13072 |
1.3708 |
0.6433 |
0.2433 |
| 0.1189 |
20.0 |
13760 |
1.3718 |
0.6412 |
0.2428 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
