|
--- |
|
language: |
|
- ar |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
base_model: openai/whisper-small |
|
datasets: |
|
- zolfa |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: Zolfa-raghadomar |
|
results: |
|
- task: |
|
type: automatic-speech-recognition |
|
name: Automatic Speech Recognition |
|
dataset: |
|
name: Zolfa Dataset |
|
type: zolfa |
|
args: 'config: ar, split: test' |
|
metrics: |
|
- type: wer |
|
value: 8.571428571428571 |
|
name: Wer |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# Zolfa-raghadomar |
|
|
|
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Zolfa Dataset dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2396 |
|
- Wer: 8.5714 |
|
|
|
## 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: 4 |
|
- 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: 5 |
|
- training_steps: 1000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:------:|:----:|:---------------:|:-------:| |
|
| 0.0673 | 0.6993 | 100 | 0.2047 | 12.8571 | |
|
| 0.0239 | 1.3986 | 200 | 0.2376 | 10.4082 | |
|
| 0.0087 | 2.0979 | 300 | 0.2165 | 9.7959 | |
|
| 0.009 | 2.7972 | 400 | 0.2169 | 7.9592 | |
|
| 0.0034 | 3.4965 | 500 | 0.2277 | 8.5714 | |
|
| 0.0041 | 4.1958 | 600 | 0.2401 | 8.5714 | |
|
| 0.0032 | 4.8951 | 700 | 0.2395 | 7.9592 | |
|
| 0.0007 | 5.5944 | 800 | 0.2430 | 8.5714 | |
|
| 0.0002 | 6.2937 | 900 | 0.2380 | 8.5714 | |
|
| 0.0015 | 6.9930 | 1000 | 0.2396 | 8.5714 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
