|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- superb |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: wav2vec2-base-finetuned-ks |
|
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-ks |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the superb dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0941 |
|
- Accuracy: 0.9801 |
|
|
|
## 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: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.814 | 1.0 | 399 | 0.6793 | 0.7992 | |
|
| 0.333 | 2.0 | 798 | 0.2157 | 0.9715 | |
|
| 0.2253 | 3.0 | 1197 | 0.1269 | 0.9787 | |
|
| 0.1824 | 4.0 | 1597 | 0.0983 | 0.9800 | |
|
| 0.1414 | 5.0 | 1995 | 0.0941 | 0.9801 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.29.0.dev0 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
