Fi2Hr-wav2vec2-large-xls-r-300m-finnish-colab
This model was trained from scratch on the voxpopuli dataset. It achieves the following results on the evaluation set:
- Loss: 3.5849
- Wer: 0.9766
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=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.4545 | 10.67 | 800 | 2.4336 | 0.9655 |
0.1599 | 21.33 | 1600 | 2.8208 | 0.9692 |
0.0758 | 32.0 | 2400 | 3.5207 | 0.9803 |
0.0405 | 42.67 | 3200 | 3.5849 | 0.9766 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.14.7
- Tokenizers 0.15.0
- Downloads last month
- 9