<!-- 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-bemba-10hrs
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: 0.3022
- Wer: 0.3976
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: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
3.4544 | 1.07 | 400 | 0.4912 | 0.6813 |
0.662 | 2.14 | 800 | 0.3667 | 0.5690 |
0.4601 | 3.22 | 1200 | 0.2792 | 0.4819 |
0.3816 | 4.29 | 1600 | 0.2828 | 0.4608 |
0.3012 | 5.36 | 2000 | 0.2881 | 0.4651 |
0.2427 | 6.43 | 2400 | 0.2758 | 0.4219 |
0.1888 | 7.51 | 2800 | 0.2743 | 0.4094 |
0.1559 | 8.58 | 3200 | 0.2893 | 0.4021 |
0.1203 | 9.65 | 3600 | 0.3022 | 0.3976 |
Framework versions
- Transformers 4.19.0.dev0
- Pytorch 1.10.0+cu111
- Datasets 2.1.0
- Tokenizers 0.12.1