wav2vec2-finetuned-wolofdata2
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: 0.1969
- Wer: 0.1897
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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: 300
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 12.9468 | 0.75 | 100 | 4.0058 | 1.0 |
| 3.3471 | 1.49 | 200 | 3.1350 | 1.0 |
| 3.014 | 2.24 | 300 | 2.4949 | 0.9997 |
| 1.5935 | 2.99 | 400 | 0.8807 | 0.72 |
| 0.7567 | 3.73 | 500 | 0.4770 | 0.47 |
| 0.4514 | 4.48 | 600 | 0.3082 | 0.3003 |
| 0.2778 | 5.22 | 700 | 0.2297 | 0.2244 |
| 0.2062 | 5.97 | 800 | 0.1969 | 0.1897 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu113
- Datasets 1.18.3
- Tokenizers 0.10.3