|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: Audioclasswindows |
|
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. --> |
|
|
|
# Audioclasswindows |
|
|
|
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: 2.6744 |
|
- Accuracy: 0.0796 |
|
|
|
## 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: 16 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 0.8 | 3 | 2.6364 | 0.1062 | |
|
| No log | 1.87 | 7 | 2.6465 | 0.0442 | |
|
| 2.6363 | 2.93 | 11 | 2.6420 | 0.0973 | |
|
| 2.6363 | 4.0 | 15 | 2.6543 | 0.0796 | |
|
| 2.6363 | 4.8 | 18 | 2.6579 | 0.0885 | |
|
| 2.6244 | 5.87 | 22 | 2.6587 | 0.0885 | |
|
| 2.6244 | 6.93 | 26 | 2.6608 | 0.0885 | |
|
| 2.6103 | 8.0 | 30 | 2.6632 | 0.0796 | |
|
| 2.6103 | 8.8 | 33 | 2.6664 | 0.0796 | |
|
| 2.6103 | 9.87 | 37 | 2.6692 | 0.0796 | |
|
| 2.6019 | 10.93 | 41 | 2.6722 | 0.0796 | |
|
| 2.6019 | 12.0 | 45 | 2.6740 | 0.0796 | |
|
| 2.6019 | 12.8 | 48 | 2.6744 | 0.0796 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
