|
--- |
|
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: 0.0419 |
|
- Accuracy: 0.995 |
|
- F1: 0.9950 |
|
- Recall: 0.9950 |
|
- Precision: 0.9951 |
|
- Mcc: 0.9938 |
|
- Auc: 0.9987 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|:------:|:------:| |
|
| 0.8258 | 1.0 | 200 | 0.7423 | 0.76 | 0.6973 | 0.76 | 0.6699 | 0.7402 | 0.9766 | |
|
| 0.1609 | 2.0 | 400 | 0.1559 | 0.96 | 0.9596 | 0.96 | 0.9644 | 0.9513 | 0.9997 | |
|
| 0.219 | 3.0 | 600 | 0.0864 | 0.9825 | 0.9826 | 0.9825 | 0.9828 | 0.9782 | 0.9983 | |
|
| 0.0049 | 4.0 | 800 | 0.0341 | 0.995 | 0.9950 | 0.9950 | 0.9950 | 0.9938 | 0.9999 | |
|
| 0.0031 | 5.0 | 1000 | 0.1241 | 0.98 | 0.9799 | 0.9800 | 0.9808 | 0.9752 | 0.9989 | |
|
| 0.0021 | 6.0 | 1200 | 0.0394 | 0.995 | 0.9950 | 0.9950 | 0.9951 | 0.9938 | 0.9988 | |
|
| 0.0017 | 7.0 | 1400 | 0.0410 | 0.995 | 0.9950 | 0.9950 | 0.9951 | 0.9938 | 0.9993 | |
|
| 0.0015 | 8.0 | 1600 | 0.0420 | 0.995 | 0.9950 | 0.9950 | 0.9951 | 0.9938 | 0.9987 | |
|
| 0.0013 | 9.0 | 1800 | 0.0418 | 0.995 | 0.9950 | 0.9950 | 0.9951 | 0.9938 | 0.9987 | |
|
| 0.0013 | 10.0 | 2000 | 0.0419 | 0.995 | 0.9950 | 0.9950 | 0.9951 | 0.9938 | 0.9987 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
