<!-- 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. -->
xls-r-300m-bem
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1962
- Wer: 0.3219
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
2.8892 | 0.64 | 500 | 0.4485 | 0.6822 |
0.5257 | 1.29 | 1000 | 0.2625 | 0.4381 |
0.418 | 1.93 | 1500 | 0.2408 | 0.3948 |
0.3216 | 2.58 | 2000 | 0.2091 | 0.3666 |
0.2797 | 3.22 | 2500 | 0.2040 | 0.3519 |
0.2354 | 3.87 | 3000 | 0.1983 | 0.3328 |
0.1933 | 4.51 | 3500 | 0.1962 | 0.3219 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2