<!-- 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. -->
neunit-ks-20230509V2
This model is a fine-tuned version of facebook/wav2vec2-base on the superb dataset. It achieves the following results on the evaluation set:
- Loss: 0.1132
- Accuracy: 0.9857
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: 32
- eval_batch_size: 32
- seed: 0
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.8544 | 0.99 | 49 | 0.6346 | 0.8343 |
0.373 | 1.99 | 98 | 0.2942 | 0.9029 |
0.2388 | 2.98 | 147 | 0.1621 | 0.98 |
0.1545 | 4.0 | 197 | 0.1132 | 0.9857 |
0.1281 | 4.97 | 245 | 0.1036 | 0.9843 |
Framework versions
- Transformers 4.29.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3