<!-- 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-base-vios
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the vivos_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.3729
- Wer: 0.2427
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: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
4.4755 | 1.37 | 500 | 0.7991 | 0.5957 |
0.5424 | 2.75 | 1000 | 0.4290 | 0.3653 |
0.3586 | 4.12 | 1500 | 0.3809 | 0.2890 |
0.2824 | 5.49 | 2000 | 0.3808 | 0.2749 |
0.2249 | 6.87 | 2500 | 0.3467 | 0.2389 |
0.1745 | 8.24 | 3000 | 0.3688 | 0.2384 |
0.1459 | 9.61 | 3500 | 0.3729 | 0.2427 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu113
- Datasets 1.18.3
- Tokenizers 0.10.3