<!-- 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. -->
xlsr-syntesized-turkish-2-hour-llr
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.1105
- 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: 1e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 9.4081 | 1.04 | 100 | 8.3205 | 1.0 |
| 5.0295 | 2.08 | 200 | 4.3245 | 1.0 |
| 3.7196 | 3.12 | 300 | 3.8079 | 1.0 |
| 3.4558 | 4.17 | 400 | 3.5232 | 1.0 |
| 3.304 | 5.21 | 500 | 3.3519 | 1.0 |
| 3.2115 | 6.25 | 600 | 3.2609 | 1.0 |
| 3.1533 | 7.29 | 700 | 3.1903 | 1.0 |
| 3.0813 | 8.33 | 800 | 3.1409 | 1.0 |
| 3.0279 | 9.38 | 900 | 3.0815 | 1.0 |
| 2.9087 | 10.42 | 1000 | 3.0615 | 1.0 |
| 2.6893 | 11.46 | 1100 | 3.0408 | 1.0 |
| 2.4277 | 12.5 | 1200 | 3.0961 | 1.0 |
| 2.2325 | 13.54 | 1300 | 3.0973 | 1.0 |
| 2.0858 | 14.58 | 1400 | 3.1216 | 1.0 |
| 1.9604 | 15.62 | 1500 | 3.1271 | 1.0 |
| 1.8766 | 16.67 | 1600 | 3.1099 | 1.0 |
| 1.8093 | 17.71 | 1700 | 3.1191 | 1.0 |
| 1.7577 | 18.75 | 1800 | 3.1191 | 1.0 |
| 1.7174 | 19.79 | 1900 | 3.1105 | 1.0 |
Framework versions
- Transformers 4.26.0
- Pytorch 2.0.1+cu118
- Datasets 2.9.0
- Tokenizers 0.13.3
