|
|
--- |
|
|
library_name: transformers |
|
|
language: |
|
|
- pt |
|
|
license: apache-2.0 |
|
|
base_model: openai/whisper-large-v3 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- wer |
|
|
model-index: |
|
|
- name: Whisper LARGE PT 425 |
|
|
results: [] |
|
|
datasets: |
|
|
- inesc-id/camoes_asr |
|
|
--- |
|
|
|
|
|
<!-- 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. --> |
|
|
|
|
|
# Whisper LARGE PT 425 |
|
|
|
|
|
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on 425h of European Portuguese data. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.1162 |
|
|
- Wer: 3.9720 |
|
|
|
|
|
For additional information regarding this model please refer to the [paper](https://arxiv.org/abs/2508.19721). |
|
|
|
|
|
|
|
|
## Training procedure |
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- learning_rate: 1e-05 |
|
|
- train_batch_size: 64 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 256 |
|
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 10 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|
|:-------------:|:------:|:-----:|:---------------:|:------:| |
|
|
| 0.0037 | 7.5989 | 10000 | 0.1162 | 3.9720 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.48.2 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 3.2.0 |
|
|
- Tokenizers 0.21.0 |
