<!-- 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. -->
dys_asr_nf
This model is a fine-tuned version of facebook/wav2vec2-large-lv60 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0884
- Wer: 1.2212
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 |
---|---|---|---|---|
12.8652 | 1.36 | 500 | 3.5506 | 1.0 |
3.5628 | 2.72 | 1000 | 2.5346 | 1.0 |
1.8962 | 4.09 | 1500 | 0.7601 | 2.0 |
0.5529 | 5.45 | 2000 | 0.1421 | 1.2118 |
0.2672 | 6.81 | 2500 | 0.0884 | 1.2212 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.13.1+cu116
- Datasets 1.18.3
- Tokenizers 0.13.2