pronunciation_scoring_model_fluency
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1280
- Accuracy: 0.4003
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.114 | 0.98 | 20 | 1.1085 | 0.3267 |
| 1.0942 | 2.0 | 41 | 1.1055 | 0.3466 |
| 1.083 | 2.98 | 61 | 1.0953 | 0.3604 |
| 1.0722 | 4.0 | 82 | 1.1126 | 0.3512 |
| 1.049 | 4.98 | 102 | 1.1099 | 0.3528 |
| 1.0444 | 6.0 | 123 | 1.1120 | 0.3926 |
| 1.0314 | 6.98 | 143 | 1.1303 | 0.3819 |
| 1.0104 | 8.0 | 164 | 1.1272 | 0.3819 |
| 1.0072 | 8.98 | 184 | 1.1181 | 0.3972 |
| 0.9889 | 9.76 | 200 | 1.1280 | 0.4003 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 81