metadata
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: fr_only
results: []
fr_only
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1454
- Wer: 0.6672
- Cer: 0.3732
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 4.2678 | 0.8 | 500 | 3.9064 | 1.0 | 1.0 |
| 3.8874 | 1.61 | 1000 | 3.8322 | 1.0 | 1.0 |
| 3.7809 | 2.41 | 1500 | 3.5061 | 0.9737 | 0.8809 |
| 2.9215 | 3.21 | 2000 | 2.4683 | 0.9685 | 0.6577 |
| 2.3508 | 4.01 | 2500 | 2.1271 | 0.9144 | 0.6212 |
| 2.0152 | 4.82 | 3000 | 1.8754 | 0.8794 | 0.5677 |
| 1.6777 | 5.62 | 3500 | 1.5346 | 0.7830 | 0.4904 |
| 1.4068 | 6.42 | 4000 | 1.3605 | 0.7419 | 0.4583 |
| 1.1826 | 7.22 | 4500 | 1.2643 | 0.6912 | 0.4349 |
| 0.9938 | 8.03 | 5000 | 1.1641 | 0.7039 | 0.3977 |
| 0.7796 | 8.83 | 5500 | 1.1441 | 0.6934 | 0.3865 |
| 0.6479 | 9.63 | 6000 | 1.1454 | 0.6672 | 0.3732 |
Framework versions
- Transformers 4.36.2
- Pytorch 1.13.0+cu116
- Datasets 2.15.0
- Tokenizers 0.15.2