<!-- 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-1b-bemba-5hrs
This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2659
- Wer: 0.3884
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 400
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
2.1067 | 1.08 | 400 | 0.4681 | 0.8206 |
0.5003 | 2.16 | 800 | 0.3052 | 0.5253 |
0.3641 | 3.24 | 1200 | 0.2665 | 0.4437 |
0.2847 | 4.32 | 1600 | 0.2526 | 0.4267 |
0.2324 | 5.41 | 2000 | 0.2579 | 0.4211 |
0.1789 | 6.49 | 2400 | 0.2593 | 0.3958 |
0.1302 | 7.57 | 2800 | 0.2659 | 0.3884 |
Framework versions
- Transformers 4.19.0.dev0
- Pytorch 1.10.0+cu111
- Datasets 2.1.0
- Tokenizers 0.12.1