swahili
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0009
- Wer: 0.6055
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: 0.0001
- train_batch_size: 3
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.723 | 1.5 | 1000 | 1.1521 | 0.7429 |
| 0.8457 | 3.0 | 2000 | 1.2019 | 0.7280 |
| 0.6465 | 4.5 | 3000 | 1.0385 | 0.6602 |
| 0.5081 | 6.0 | 4000 | 0.9303 | 0.6310 |
| 0.3864 | 7.5 | 5000 | 1.0838 | 0.6240 |
| 0.3109 | 9.0 | 6000 | 1.0009 | 0.6055 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3