metadata
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-large
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec-large-en
results: []
wav2vec-large-en
This model is a fine-tuned version of facebook/wav2vec2-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 7.2821
- Wer: 1.0
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 6.0558 | 0.7042 | 100 | 7.1035 | 1.0 |
| 5.3678 | 1.4085 | 200 | 7.4719 | 1.0 |
| 5.2548 | 2.1127 | 300 | 7.3891 | 1.0 |
| 5.1982 | 2.8169 | 400 | 7.2118 | 1.0 |
| 5.1951 | 3.5211 | 500 | 7.0877 | 1.0 |
| 5.1829 | 4.2254 | 600 | 7.2987 | 1.0 |
| 5.1937 | 4.9296 | 700 | 7.3988 | 1.0 |
| 5.1905 | 5.6338 | 800 | 7.3964 | 1.0 |
| 5.2445 | 6.3380 | 900 | 7.2698 | 1.0 |
| 5.139 | 7.0423 | 1000 | 7.1558 | 1.0 |
| 5.1925 | 7.7465 | 1100 | 7.2421 | 1.0 |
| 5.2231 | 8.4507 | 1200 | 7.2611 | 1.0 |
| 5.2901 | 9.1549 | 1300 | 7.3504 | 1.0 |
| 5.0849 | 9.8592 | 1400 | 7.3211 | 1.0 |
| 5.3853 | 10.5634 | 1500 | 7.1273 | 1.0 |
| 5.2707 | 11.2676 | 1600 | 7.2369 | 1.0 |
| 5.1156 | 11.9718 | 1700 | 7.3677 | 1.0 |
| 5.1589 | 12.6761 | 1800 | 7.3260 | 1.0 |
| 5.1839 | 13.3803 | 1900 | 7.2956 | 1.0 |
| 5.3138 | 14.0845 | 2000 | 7.1808 | 1.0 |
| 5.2344 | 14.7887 | 2100 | 7.2265 | 1.0 |
| 5.1787 | 15.4930 | 2200 | 7.3030 | 1.0 |
| 5.1879 | 16.1972 | 2300 | 7.2975 | 1.0 |
| 5.106 | 16.9014 | 2400 | 7.2839 | 1.0 |
| 5.3462 | 17.6056 | 2500 | 7.2212 | 1.0 |
| 5.0687 | 18.3099 | 2600 | 7.2478 | 1.0 |
| 5.1134 | 19.0141 | 2700 | 7.2222 | 1.0 |
| 5.1133 | 19.7183 | 2800 | 7.3043 | 1.0 |
| 5.2053 | 20.4225 | 2900 | 7.3150 | 1.0 |
| 5.205 | 21.1268 | 3000 | 7.2460 | 1.0 |
| 5.2558 | 21.8310 | 3100 | 7.2312 | 1.0 |
| 5.215 | 22.5352 | 3200 | 7.2725 | 1.0 |
| 5.1499 | 23.2394 | 3300 | 7.2609 | 1.0 |
| 5.152 | 23.9437 | 3400 | 7.3052 | 1.0 |
| 5.2532 | 24.6479 | 3500 | 7.2958 | 1.0 |
| 5.3097 | 25.3521 | 3600 | 7.2818 | 1.0 |
| 5.1221 | 26.0563 | 3700 | 7.2260 | 1.0 |
| 5.2023 | 26.7606 | 3800 | 7.2648 | 1.0 |
| 5.1029 | 27.4648 | 3900 | 7.2708 | 1.0 |
| 5.085 | 28.1690 | 4000 | 7.2965 | 1.0 |
| 5.2273 | 28.8732 | 4100 | 7.2845 | 1.0 |
| 5.2394 | 29.5775 | 4200 | 7.2821 | 1.0 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1