wav2vec2-ru
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5468
- Wer: 0.4124
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: 1e-06
- train_batch_size: 1
- 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: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.511 | 0.21 | 1000 | 0.5444 | 0.4183 |
| 0.5021 | 0.43 | 2000 | 0.5727 | 0.4112 |
| 0.4746 | 0.64 | 3000 | 0.5495 | 0.4116 |
| 0.5052 | 0.85 | 4000 | 0.5468 | 0.4124 |
Framework versions
- Transformers 4.20.0
- Pytorch 1.11.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1