wav2vec2-base-finetuned-ks-de
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8987
- Accuracy: 0.7222
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: 42
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.67 | 1 | 1.9651 | 0.0 |
| No log | 1.67 | 2 | 1.8987 | 0.7222 |
| No log | 2.67 | 3 | 1.8546 | 0.7222 |
| No log | 3.67 | 4 | 1.8259 | 0.7222 |
| No log | 4.67 | 5 | 1.8121 | 0.7222 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0+cu102
- Datasets 2.3.2
- Tokenizers 0.12.1