metadata
license: apache-2.0
base_model: vitouphy/wav2vec2-xls-r-300m-english
tags:
- generated_from_trainer
model-index:
- name: wav2vec-reptiles
results: []
wav2vec-reptiles
This model is a fine-tuned version of vitouphy/wav2vec2-xls-r-300m-english on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2223.3787
- Pcc Accuracy: 0.2187
- Pcc Fluency: 0.0834
- Pcc Total Score: 0.1532
- Pcc Content: 0.2235
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.4
- num_epochs: 25
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Pcc Accuracy | Pcc Fluency | Pcc Total Score | Pcc Content |
|---|---|---|---|---|---|---|---|
| 2728.7846 | 5.0 | 100 | 3196.0576 | 0.3476 | -0.2327 | -0.3110 | 0.2340 |
| 2491.7434 | 10.0 | 200 | 2875.6025 | 0.2791 | -0.0388 | -0.0724 | 0.2475 |
| 1926.2301 | 15.0 | 300 | 2480.8772 | 0.2280 | 0.0499 | 0.1131 | 0.2334 |
| 2065.1381 | 20.0 | 400 | 2265.0391 | 0.2201 | 0.0799 | 0.1478 | 0.2238 |
| 1903.073 | 25.0 | 500 | 2223.3787 | 0.2187 | 0.0834 | 0.1532 | 0.2235 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.17.0
- Tokenizers 0.15.1