<!-- 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. -->
f03_main
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: 0.0768
- Wer: 1.0597
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: 7
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
9.4936 | 0.93 | 500 | 4.0912 | 1.0 |
2.6311 | 1.87 | 1000 | 1.7825 | 2.4286 |
1.0606 | 2.8 | 1500 | 0.3506 | 1.6247 |
0.3205 | 3.74 | 2000 | 0.1833 | 1.1471 |
0.1583 | 4.67 | 2500 | 0.1143 | 1.3198 |
0.0759 | 5.61 | 3000 | 0.0881 | 1.3561 |
0.0621 | 6.54 | 3500 | 0.0768 | 1.0597 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.13.1+cu116
- Datasets 1.18.3
- Tokenizers 0.13.2