|
--- |
|
base_model: vinai/PhoWhisper-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: whisper-small2-vi |
|
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. --> |
|
|
|
# whisper-small2-vi |
|
|
|
This model is a fine-tuned version of [vinai/PhoWhisper-small](https://huggingface.co/vinai/PhoWhisper-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2336 |
|
- Wer: 7.8066 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 8 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:| |
|
| 0.3058 | 1.6 | 1000 | 0.3433 | 28.2955 | |
|
| 0.1055 | 3.2 | 2000 | 0.3438 | 10.0351 | |
|
| 0.0521 | 4.8 | 3000 | 0.2550 | 7.4959 | |
|
| 0.0073 | 6.4 | 4000 | 0.2338 | 7.8336 | |
|
| 0.0032 | 8.0 | 5000 | 0.2336 | 7.8066 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.0.dev0 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
