|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- recall |
|
- precision |
|
model-index: |
|
- name: wav2vec2-base-finetuned-common_voice |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# wav2vec2-base-finetuned-common_voice |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0870 |
|
- Accuracy: 0.9875 |
|
- F1: 0.9875 |
|
- Recall: 0.9875 |
|
- Precision: 0.9877 |
|
- Mcc: 0.9844 |
|
- Auc: 0.9968 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- 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 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision | Mcc | Auc | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|:------:|:------:| |
|
| 0.9826 | 1.0 | 200 | 0.9330 | 0.715 | 0.6769 | 0.7150 | 0.7516 | 0.6708 | 0.9379 | |
|
| 0.2818 | 2.0 | 400 | 0.5294 | 0.8425 | 0.8362 | 0.8425 | 0.8731 | 0.8133 | 0.9738 | |
|
| 0.1229 | 3.0 | 600 | 0.2185 | 0.945 | 0.9455 | 0.945 | 0.9476 | 0.9317 | 0.9917 | |
|
| 0.0094 | 4.0 | 800 | 0.2905 | 0.9425 | 0.9428 | 0.9425 | 0.9476 | 0.9293 | 0.9932 | |
|
| 0.0256 | 5.0 | 1000 | 0.1565 | 0.97 | 0.9702 | 0.97 | 0.9720 | 0.9629 | 0.9972 | |
|
| 0.0032 | 6.0 | 1200 | 0.1577 | 0.9775 | 0.9775 | 0.9775 | 0.9778 | 0.9720 | 0.9941 | |
|
| 0.0869 | 7.0 | 1400 | 0.1017 | 0.9825 | 0.9824 | 0.9825 | 0.9826 | 0.9782 | 0.9965 | |
|
| 0.0019 | 8.0 | 1600 | 0.1194 | 0.9775 | 0.9776 | 0.9775 | 0.9783 | 0.9720 | 0.9967 | |
|
| 0.0017 | 9.0 | 1800 | 0.0947 | 0.985 | 0.9850 | 0.9850 | 0.9851 | 0.9813 | 0.9972 | |
|
| 0.0016 | 10.0 | 2000 | 0.0870 | 0.9875 | 0.9875 | 0.9875 | 0.9877 | 0.9844 | 0.9968 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
