|
--- |
|
license: apache-2.0 |
|
base_model: duytran3112/whisper-sm-vivos |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: whisper-vietnamese-3 |
|
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-vietnamese-3 |
|
|
|
This model is a fine-tuned version of [duytran3112/whisper-sm-vivos](https://huggingface.co/duytran3112/whisper-sm-vivos) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6164 |
|
- Wer: 104.1257 |
|
- Cer: 100.8264 |
|
|
|
## 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: 4000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:| |
|
| 0.0204 | 7.19 | 1000 | 0.4900 | 123.6149 | 105.0861 | |
|
| 0.0022 | 14.39 | 2000 | 0.5671 | 111.9607 | 104.7015 | |
|
| 0.0009 | 21.58 | 3000 | 0.6017 | 109.1316 | 101.5308 | |
|
| 0.0006 | 28.78 | 4000 | 0.6164 | 104.1257 | 100.8264 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|