wav2vec2-large-xlsr-53-kk-6h-16epoch
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5374
- Wer: 0.4968
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: 0.000222
- 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: 1000
- num_epochs: 16
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.7638 | 3.3 | 400 | 1.9097 | 0.9994 |
| 0.4138 | 6.61 | 800 | 0.6118 | 0.6814 |
| 0.1943 | 9.91 | 1200 | 0.5067 | 0.5564 |
| 0.097 | 13.22 | 1600 | 0.5374 | 0.4968 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.11.0+cu113
- Datasets 2.8.0
- Tokenizers 0.13.2