metadata
license: mit
base_model: arslanarjumand/wav2vec-reptiles
tags:
- generated_from_trainer
model-index:
- name: wav2vec-reptiles
results: []
wav2vec-reptiles
This model is a fine-tuned version of arslanarjumand/wav2vec-reptiles on the None dataset. It achieves the following results on the evaluation set:
- Loss: 180.5618
- Pcc Accuracy: 0.7344
- Pcc Fluency: 0.7572
- Pcc Total Score: 0.7949
- Pcc Content: 0.7727
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: 2.5e-05
- train_batch_size: 4
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.5
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Pcc Accuracy | Pcc Fluency | Pcc Total Score | Pcc Content |
|---|---|---|---|---|---|---|---|
| 323.2938 | 2.13 | 500 | 333.4772 | 0.4645 | 0.5166 | 0.5181 | 0.4915 |
| 274.2192 | 4.27 | 1000 | 259.5493 | 0.5725 | 0.6371 | 0.6430 | 0.6182 |
| 287.9362 | 6.4 | 1500 | 291.9187 | 0.6475 | 0.6895 | 0.7121 | 0.6902 |
| 273.6328 | 8.54 | 2000 | 229.1164 | 0.6884 | 0.7243 | 0.7522 | 0.7285 |
| 211.4504 | 10.67 | 2500 | 223.4485 | 0.7087 | 0.7420 | 0.7727 | 0.7499 |
| 162.7622 | 12.81 | 3000 | 180.6950 | 0.7302 | 0.7557 | 0.7918 | 0.7695 |
| 194.6916 | 14.94 | 3500 | 180.5618 | 0.7344 | 0.7572 | 0.7949 | 0.7727 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.17.1
- Tokenizers 0.15.1