|
--- |
|
language: |
|
- hre |
|
license: apache-2.0 |
|
base_model: openai/whisper-small |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- ntviet/Hre-audio-dataset4 |
|
model-index: |
|
- name: Whisper Small Hre 4.3 - male and female voice - 600 steps, metric CER, skip_special_tokens |
|
False |
|
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 Small Hre 4.3 - male and female voice - 600 steps, metric CER, skip_special_tokens False |
|
|
|
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Hre audio dataset 4 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0588 |
|
- Cer Ortho: 0.0268 |
|
- Cer: 2.2959 |
|
|
|
## 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: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant_with_warmup |
|
- lr_scheduler_warmup_steps: 50 |
|
- training_steps: 600 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Cer Ortho | Cer | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:| |
|
| 0.1153 | 2.48 | 600 | 0.0588 | 0.0268 | 2.2959 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
