|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: openai/whisper-large-v3 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- wer |
|
|
model-index: |
|
|
- name: ap-xSqNwzGtnWYrDqwzSihwx4 |
|
|
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. --> |
|
|
|
|
|
# ap-xSqNwzGtnWYrDqwzSihwx4 |
|
|
|
|
|
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.3177 |
|
|
- Model Preparation Time: 0.0221 |
|
|
- Wer: 0.1185 |
|
|
|
|
|
## 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: 3e-07 |
|
|
- train_batch_size: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 8 |
|
|
- total_train_batch_size: 64 |
|
|
- optimizer: Use OptimizerNames.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_steps: 400 |
|
|
- num_epochs: 10 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Wer | |
|
|
|:-------------:|:------:|:----:|:---------------:|:----------------------:|:------:| |
|
|
| 0.8267 | 0.9791 | 41 | 0.8658 | 0.0221 | 0.1948 | |
|
|
| 0.7767 | 1.9791 | 82 | 0.8411 | 0.0221 | 0.1936 | |
|
|
| 0.7309 | 2.9791 | 123 | 0.7830 | 0.0221 | 0.1889 | |
|
|
| 0.6692 | 3.9791 | 164 | 0.7042 | 0.0221 | 0.1764 | |
|
|
| 0.6023 | 4.9791 | 205 | 0.6325 | 0.0221 | 0.1657 | |
|
|
| 0.4923 | 5.9791 | 246 | 0.5603 | 0.0221 | 0.1577 | |
|
|
| 0.3512 | 6.9791 | 287 | 0.4087 | 0.0221 | 0.1533 | |
|
|
| 0.275 | 7.9791 | 328 | 0.3569 | 0.0221 | 0.1279 | |
|
|
| 0.2927 | 8.9791 | 369 | 0.3339 | 0.0221 | 0.1217 | |
|
|
| 0.2657 | 9.9791 | 410 | 0.3177 | 0.0221 | 0.1185 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.48.3 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.2.0 |
|
|
- Tokenizers 0.21.0 |
|
|
|
