<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
wav2vec2-hbtest-2
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: 5.9927
- Wer: 1.1562
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: 0.0001
- 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: 500
- num_epochs: 40
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.6105 | 6.41 | 1000 | 4.9969 | 1.2600 |
| 0.3723 | 12.82 | 2000 | 5.1370 | 1.1185 |
| 0.1537 | 19.23 | 3000 | 5.5541 | 1.1419 |
| 0.0992 | 25.64 | 4000 | 5.9309 | 1.1269 |
| 0.0722 | 32.05 | 5000 | 5.9545 | 1.1628 |
| 0.0593 | 38.46 | 6000 | 5.9927 | 1.1562 |
Framework versions
- Transformers 4.20.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 2.2.3.dev0
- Tokenizers 0.12.1
