ezra-wav2vec2-large-xls-r-300m-indonesian-Fleurs-CL-colab
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4675
- Wer: 0.4520
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- 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: 250
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 5.8777 | 2.02 | 200 | 2.9207 | 1.0 |
| 2.913 | 4.03 | 400 | 2.8439 | 1.0 |
| 2.23 | 6.05 | 600 | 0.9957 | 0.8677 |
| 0.5692 | 8.06 | 800 | 0.5358 | 0.5346 |
| 0.2491 | 10.08 | 1000 | 0.4675 | 0.4520 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1