<!-- 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-large-xlsr-es-col-pro
This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-spanish on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0636
- Wer: 0.0507
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
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.1032 | 7.4 | 400 | 0.0618 | 0.0656 |
0.0687 | 14.81 | 800 | 0.0670 | 0.0619 |
0.0402 | 22.22 | 1200 | 0.0693 | 0.0573 |
0.0252 | 29.62 | 1600 | 0.0636 | 0.0507 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.1+cu102
- Datasets 1.13.3
- Tokenizers 0.10.3