Nystrom-W2V2-100hrs-landmarks-128-take-1
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 31.3614
- Wer: 0.1689
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: 0.0005
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 64
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 443.6301 | 9.01 | 1000 | 39.1720 | 0.3382 |
| 86.4447 | 18.02 | 2000 | 28.0213 | 0.2008 |
| 42.4394 | 27.03 | 3000 | 31.3614 | 0.1689 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1
- Datasets 2.7.0
- Tokenizers 0.11.0