|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: wav2vec2-base |
|
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 |
|
|
|
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: 0.7306 |
|
- Accuracy: 0.8322 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:| |
|
| 2.0418 | 0.9851 | 33 | 2.0022 | 0.3299 | |
|
| 1.7549 | 2.0 | 67 | 1.6488 | 0.4602 | |
|
| 1.3727 | 2.9851 | 100 | 1.4025 | 0.5970 | |
|
| 1.1483 | 4.0 | 134 | 1.1598 | 0.6739 | |
|
| 1.0037 | 4.9851 | 167 | 0.9707 | 0.7516 | |
|
| 0.8469 | 6.0 | 201 | 0.8492 | 0.7994 | |
|
| 0.8115 | 6.9851 | 234 | 0.7889 | 0.8097 | |
|
| 0.7371 | 8.0 | 268 | 0.7440 | 0.8247 | |
|
| 0.6778 | 8.9851 | 301 | 0.7367 | 0.8304 | |
|
| 0.6806 | 9.8507 | 330 | 0.7306 | 0.8322 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
