wav2vec2-large-xls-r-300m-turkish-colab2
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 0.3738
- Wer: 0.3532
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: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.9022 | 3.7 | 400 | 0.6778 | 0.7414 |
| 0.4106 | 7.4 | 800 | 0.4123 | 0.5049 |
| 0.1862 | 11.11 | 1200 | 0.4260 | 0.4232 |
| 0.1342 | 14.81 | 1600 | 0.3951 | 0.4097 |
| 0.0997 | 18.51 | 2000 | 0.4100 | 0.3999 |
| 0.0782 | 22.22 | 2400 | 0.3918 | 0.3875 |
| 0.059 | 25.92 | 2800 | 0.3803 | 0.3698 |
| 0.0474 | 29.63 | 3200 | 0.3738 | 0.3532 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1