<!-- 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. -->
small_finetune_M01_2
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.1910
- Wer: 1.0
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: 0.001
- train_batch_size: 15
- 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: 600
- num_epochs: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 13.822 | 500.0 | 3000 | 2.7772 | 1.0 |
| 0.8369 | 1000.0 | 6000 | 2.9828 | 1.0 |
| 0.7474 | 1500.0 | 9000 | 3.1834 | 1.0 |
| 0.7125 | 2000.0 | 12000 | 3.1910 | 1.0 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.2+cu102
- Datasets 2.3.2
- Tokenizers 0.12.1
