|
|
--- |
|
|
library_name: transformers |
|
|
language: |
|
|
- ar |
|
|
license: apache-2.0 |
|
|
base_model: openai/whisper-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- wer |
|
|
model-index: |
|
|
- name: Whisper base AR - BA |
|
|
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 base AR - BA |
|
|
|
|
|
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the quran-ayat-speech-to-text dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0867 |
|
|
- Wer: 0.1925 |
|
|
|
|
|
## 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: 0.0001 |
|
|
- train_batch_size: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 32 |
|
|
- 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: 500 |
|
|
- num_epochs: 15 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|
|:-------------:|:-------:|:----:|:---------------:|:------:| |
|
|
| 1.7381 | 1.0 | 469 | 0.0864 | 0.1945 | |
|
|
| 1.6182 | 2.0 | 938 | 0.0902 | 0.2013 | |
|
|
| 1.2194 | 3.0 | 1407 | 0.0893 | 0.1911 | |
|
|
| 1.0951 | 4.0 | 1876 | 0.0881 | 0.2001 | |
|
|
| 1.0233 | 5.0 | 2345 | 0.0867 | 0.1979 | |
|
|
| 0.9062 | 6.0 | 2814 | 0.0864 | 0.1995 | |
|
|
| 0.8866 | 7.0 | 3283 | 0.0852 | 0.1992 | |
|
|
| 0.8074 | 8.0 | 3752 | 0.0858 | 0.1922 | |
|
|
| 0.7585 | 9.0 | 4221 | 0.0853 | 0.1882 | |
|
|
| 0.6978 | 10.0 | 4690 | 0.0849 | 0.1911 | |
|
|
| 0.6625 | 11.0 | 5159 | 0.0845 | 0.1901 | |
|
|
| 0.6375 | 12.0 | 5628 | 0.0839 | 0.1861 | |
|
|
| 0.6057 | 13.0 | 6097 | 0.0838 | 0.1883 | |
|
|
| 0.5872 | 14.0 | 6566 | 0.0839 | 0.1895 | |
|
|
| 0.5605 | 14.9685 | 7020 | 0.0838 | 0.1891 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.51.3 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 3.6.0 |
|
|
- Tokenizers 0.21.1 |
|
|
|
