|
|
--- |
|
|
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: 0.1077 |
|
|
- Wer: 0.2309 |
|
|
|
|
|
## 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: 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: 500 |
|
|
- num_epochs: 15 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|
|:-------------:|:-------:|:----:|:---------------:|:------:| |
|
|
| 3.3412 | 1.0 | 157 | 0.1041 | 0.2149 | |
|
|
| 3.0121 | 2.0 | 314 | 0.1054 | 0.2123 | |
|
|
| 2.6811 | 3.0 | 471 | 0.1033 | 0.2079 | |
|
|
| 2.2468 | 4.0 | 628 | 0.1062 | 0.2163 | |
|
|
| 2.1438 | 5.0 | 785 | 0.1029 | 0.2168 | |
|
|
| 1.8098 | 6.0 | 942 | 0.1035 | 0.2131 | |
|
|
| 1.7488 | 7.0 | 1099 | 0.1023 | 0.2190 | |
|
|
| 1.52 | 8.0 | 1256 | 0.1020 | 0.2116 | |
|
|
| 1.431 | 9.0 | 1413 | 0.1013 | 0.2112 | |
|
|
| 1.3151 | 10.0 | 1570 | 0.1005 | 0.2168 | |
|
|
| 1.2219 | 11.0 | 1727 | 0.1011 | 0.2107 | |
|
|
| 1.1879 | 12.0 | 1884 | 0.1003 | 0.2097 | |
|
|
| 1.1158 | 13.0 | 2041 | 0.1007 | 0.2098 | |
|
|
| 1.0995 | 14.0 | 2198 | 0.0998 | 0.2095 | |
|
|
| 1.0596 | 14.9088 | 2340 | 0.1001 | 0.2107 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.51.3 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 3.6.0 |
|
|
- Tokenizers 0.21.1 |
|
|
|
