---
library_name: transformers
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: base_sami_22k_ft_pseudo_widv_ep60_tde
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# base_sami_22k_ft_pseudo_widv_ep60_tde

This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 156.9329
- Wer: 0.1783
- Cer: 0.0520

## 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: 0.0005
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.25
- num_epochs: 60.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Wer    | Cer    |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
| 4165.6836     | 1.0   | 972   | 257.4717        | 0.5061 | 0.1236 |
| 711.8623      | 2.0   | 1944  | 178.0096        | 0.3002 | 0.0752 |
| 536.9188      | 3.0   | 2916  | 177.6306        | 0.3027 | 0.0734 |
| 499.5686      | 4.0   | 3888  | 160.8973        | 0.2520 | 0.0654 |
| 489.7358      | 5.0   | 4860  | 174.7495        | 0.2900 | 0.0775 |
| 508.3668      | 6.0   | 5832  | 193.4865        | 0.2944 | 0.0783 |
| 537.328       | 7.0   | 6804  | 230.1123        | 0.3104 | 0.0846 |
| 553.6925      | 8.0   | 7776  | 256.9771        | 0.3465 | 0.1000 |
| 581.7494      | 9.0   | 8748  | 254.6887        | 0.3680 | 0.1056 |
| 623.7695      | 10.0  | 9720  | 268.8913        | 0.3810 | 0.1115 |
| 652.2123      | 11.0  | 10692 | 315.2755        | 0.4066 | 0.1199 |
| 702.8481      | 12.0  | 11664 | 314.9687        | 0.4256 | 0.1261 |
| 743.4121      | 13.0  | 12636 | 311.7790        | 0.5521 | 0.1613 |
| 799.5601      | 14.0  | 13608 | 359.8279        | 0.4546 | 0.1385 |
| 816.097       | 15.0  | 14580 | 376.9053        | 0.5721 | 0.1836 |
| 815.892       | 16.0  | 15552 | 378.6718        | 0.5346 | 0.1670 |
| 803.2213      | 17.0  | 16524 | 358.1064        | 0.4638 | 0.1451 |
| 783.7681      | 18.0  | 17496 | 332.4148        | 0.4775 | 0.1448 |
| 730.573       | 19.0  | 18468 | 312.7887        | 0.4548 | 0.1391 |
| 722.3447      | 20.0  | 19440 | 316.9329        | 0.4269 | 0.1279 |
| 683.925       | 21.0  | 20412 | 290.0936        | 0.4145 | 0.1273 |
| 650.4165      | 22.0  | 21384 | 288.4570        | 0.3989 | 0.1194 |
| 631.0532      | 23.0  | 22356 | 271.8179        | 0.4043 | 0.1208 |
| 617.0345      | 24.0  | 23328 | 240.8433        | 0.3880 | 0.1139 |
| 579.2521      | 25.0  | 24300 | 261.6252        | 0.3954 | 0.1137 |
| 571.9061      | 26.0  | 25272 | 248.2078        | 0.3651 | 0.1068 |
| 535.8284      | 27.0  | 26244 | 210.3216        | 0.3549 | 0.1017 |
| 528.5526      | 28.0  | 27216 | 223.0247        | 0.3554 | 0.1005 |
| 495.6612      | 29.0  | 28188 | 214.1045        | 0.3421 | 0.1011 |
| 489.6183      | 30.0  | 29160 | 223.9064        | 0.3301 | 0.0963 |
| 465.3683      | 31.0  | 30132 | 204.1657        | 0.3408 | 0.0976 |
| 447.7585      | 32.0  | 31104 | 204.1836        | 0.3147 | 0.0902 |
| 430.5009      | 33.0  | 32076 | 199.8400        | 0.3149 | 0.0906 |
| 423.8555      | 34.0  | 33048 | 188.0466        | 0.2939 | 0.0840 |
| 409.8573      | 35.0  | 34020 | 204.4093        | 0.2827 | 0.0807 |
| 385.368       | 36.0  | 34992 | 187.5865        | 0.2911 | 0.0833 |
| 372.0869      | 37.0  | 35964 | 181.9698        | 0.2730 | 0.0770 |
| 360.2271      | 38.0  | 36936 | 181.9897        | 0.2687 | 0.0768 |
| 340.9098      | 39.0  | 37908 | 188.7458        | 0.2650 | 0.0775 |
| 329.051       | 40.0  | 38880 | 165.1118        | 0.2632 | 0.0753 |
| 311.5036      | 41.0  | 39852 | 184.7068        | 0.2631 | 0.0730 |
| 300.7056      | 42.0  | 40824 | 169.6482        | 0.2503 | 0.0715 |
| 293.3254      | 43.0  | 41796 | 156.1380        | 0.2447 | 0.0705 |
| 272.1289      | 44.0  | 42768 | 174.9299        | 0.2404 | 0.0683 |
| 266.0369      | 45.0  | 43740 | 156.8380        | 0.2368 | 0.0673 |
| 251.5002      | 46.0  | 44712 | 170.4171        | 0.2351 | 0.0665 |
| 235.648       | 47.0  | 45684 | 159.8278        | 0.2227 | 0.0626 |
| 229.8135      | 48.0  | 46656 | 163.2967        | 0.2198 | 0.0625 |
| 220.4877      | 49.0  | 47628 | 167.3510        | 0.2138 | 0.0612 |
| 210.467       | 50.0  | 48600 | 163.8741        | 0.2138 | 0.0615 |
| 208.0692      | 51.0  | 49572 | 159.9132        | 0.2048 | 0.0587 |
| 188.9099      | 52.0  | 50544 | 160.8002        | 0.2096 | 0.0596 |
| 183.2089      | 53.0  | 51516 | 154.5008        | 0.1979 | 0.0564 |
| 174.8595      | 54.0  | 52488 | 157.2374        | 0.1964 | 0.0560 |
| 167.0076      | 55.0  | 53460 | 157.2821        | 0.1918 | 0.0550 |
| 162.867       | 56.0  | 54432 | 158.1763        | 0.1851 | 0.0539 |
| 154.225       | 57.0  | 55404 | 157.7223        | 0.1829 | 0.0532 |
| 149.2202      | 58.0  | 56376 | 159.2531        | 0.1818 | 0.0528 |
| 144.8521      | 59.0  | 57348 | 158.1030        | 0.1796 | 0.0522 |
| 145.8063      | 60.0  | 58320 | 156.3732        | 0.1787 | 0.0519 |


### Framework versions

- Transformers 4.48.3
- Pytorch 2.5.1
- Datasets 3.2.0
- Tokenizers 0.21.0