wav2vec2-base-checkpoint-3
This model is a fine-tuned version of jiobiala24/wav2vec2-base-checkpoint-2 on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 1.7007
- Wer: 0.5514
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: 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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.358 | 14.8 | 400 | 1.4841 | 0.5338 |
| 0.1296 | 29.62 | 800 | 1.7007 | 0.5514 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu111
- Datasets 1.13.3
- Tokenizers 0.10.3