|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: openai/whisper-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: fs-w-xavier-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. --> |
|
|
|
# fs-w-xavier-base |
|
|
|
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3748 |
|
- Wer: 90.8832 |
|
- Cer: 69.2460 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 16 |
|
- 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_steps: 500 |
|
- training_steps: 5000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | |
|
|:-------------:|:-------:|:----:|:---------------:|:--------:|:-------:| |
|
| 3.8293 | 4.5872 | 500 | 3.9014 | 98.4330 | 73.8234 | |
|
| 0.9253 | 9.1743 | 1000 | 1.1787 | 101.2821 | 77.9887 | |
|
| 0.3997 | 13.7615 | 1500 | 0.6684 | 98.9079 | 76.8980 | |
|
| 0.3313 | 18.3486 | 2000 | 0.4931 | 97.4359 | 79.5259 | |
|
| 0.2974 | 22.9358 | 2500 | 0.4656 | 109.0693 | 83.0385 | |
|
| 0.2635 | 27.5229 | 3000 | 0.4219 | 103.5138 | 78.6843 | |
|
| 0.2241 | 32.1101 | 3500 | 0.4047 | 100.5698 | 77.2587 | |
|
| 0.1939 | 36.6972 | 4000 | 0.3893 | 89.9810 | 69.3404 | |
|
| 0.1718 | 41.2844 | 4500 | 0.3807 | 87.8443 | 67.3738 | |
|
| 0.1471 | 45.8716 | 5000 | 0.3748 | 90.8832 | 69.2460 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.1 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.20.0 |
|
|