URDU-ASR
This model was trained from scratch on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6632
- Wer: 0.4968
- Cer: 0.2099
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=(0.85,0.9) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 1.9625 | 1.0 | 341 | 0.7371 | 0.5348 | 0.2190 |
| 0.2156 | 2.0 | 683 | 0.7057 | 0.5103 | 0.2169 |
| 0.2451 | 3.0 | 1024 | 0.6654 | 0.5161 | 0.2214 |
| 0.199 | 4.0 | 1366 | 0.6707 | 0.5089 | 0.2153 |
| 0.1657 | 4.99 | 1705 | 0.6632 | 0.4968 | 0.2099 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1