wav2vec2-large-xlsr-53-urdu
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2272
- Wer: 0.7317
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.1845 | 3.23 | 100 | 1.5430 | 0.9350 |
| 1.2003 | 6.45 | 200 | 1.4209 | 0.9024 |
| 1.1809 | 9.68 | 300 | 1.3830 | 0.8862 |
| 0.9774 | 12.9 | 400 | 1.3359 | 0.8049 |
| 0.8869 | 16.13 | 500 | 1.2775 | 0.8211 |
| 0.6738 | 19.35 | 600 | 1.2272 | 0.7317 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
- Downloads last month
- -