<!-- 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-53-english
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3950
- Wer: 0.3496
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: 8
- 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: 1000
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
3.4499 | 1.0 | 500 | 1.4091 | 0.9755 |
0.7934 | 2.01 | 1000 | 0.5071 | 0.5282 |
0.43 | 3.01 | 1500 | 0.4686 | 0.4661 |
0.2848 | 4.02 | 2000 | 0.4051 | 0.4136 |
0.2035 | 5.02 | 2500 | 0.4133 | 0.3982 |
0.1612 | 6.02 | 3000 | 0.3933 | 0.3889 |
0.1212 | 7.03 | 3500 | 0.3841 | 0.3536 |
0.1029 | 8.03 | 4000 | 0.3999 | 0.3607 |
0.0822 | 9.04 | 4500 | 0.3950 | 0.3496 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.12.1+cu113
- Datasets 1.18.3
- Tokenizers 0.12.1