|
---
|
|
license: apache-2.0
|
|
base_model: facebook/wav2vec2-base
|
|
tags:
|
|
- generated_from_trainer
|
|
metrics:
|
|
- accuracy
|
|
- precision
|
|
- recall
|
|
- f1
|
|
model-index:
|
|
- name: wav2vec2-classifier
|
|
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-classifier
|
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 3.0684
|
|
- Accuracy: 0.4474
|
|
- Precision: 0.3646
|
|
- Recall: 0.4474
|
|
- F1: 0.3683
|
|
- Binary: 0.6094
|
|
|
|
## 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
|
|
- num_epochs: 10
|
|
- mixed_precision_training: Native AMP
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Binary |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
|
|
| No log | 0.96 | 50 | 4.2611 | 0.0647 | 0.0196 | 0.0647 | 0.0252 | 0.3121 |
|
|
| 4.403 | 1.91 | 100 | 3.9746 | 0.0889 | 0.0305 | 0.0889 | 0.0343 | 0.3509 |
|
|
| 4.1379 | 2.87 | 150 | 3.7561 | 0.1698 | 0.0733 | 0.1698 | 0.0880 | 0.4135 |
|
|
| 3.8988 | 3.83 | 200 | 3.5600 | 0.2372 | 0.1619 | 0.2372 | 0.1527 | 0.4652 |
|
|
| 3.6407 | 4.78 | 250 | 3.4072 | 0.3019 | 0.2248 | 0.3019 | 0.2174 | 0.5100 |
|
|
| 3.5551 | 5.74 | 300 | 3.2951 | 0.3720 | 0.2851 | 0.3720 | 0.2858 | 0.5555 |
|
|
| 3.4319 | 6.7 | 350 | 3.2052 | 0.4070 | 0.3239 | 0.4070 | 0.3214 | 0.5803 |
|
|
| 3.3287 | 7.66 | 400 | 3.1429 | 0.4151 | 0.3738 | 0.4151 | 0.3421 | 0.5868 |
|
|
| 3.1949 | 8.61 | 450 | 3.0862 | 0.4555 | 0.3707 | 0.4555 | 0.3759 | 0.6178 |
|
|
| 3.2056 | 9.57 | 500 | 3.0684 | 0.4474 | 0.3646 | 0.4474 | 0.3683 | 0.6094 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.38.2
|
|
- Pytorch 2.3.0
|
|
- Datasets 2.19.1
|
|
- Tokenizers 0.15.1
|
|
|