metadata
library_name: transformers
language:
- ar
base_model: Ibrhm-S/arabic-speech-to-text
tags:
- generated_from_trainer
datasets:
- Ibrhm-S/arabic-speech-to-text
metrics:
- wer
model-index:
- name: Whisper Small Ar - Ibrhm S
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: arabic-speech-to-text
type: Ibrhm-S/arabic-speech-to-text
args: 'config: ar, split: test'
metrics:
- name: Wer
type: wer
value: 96.58314350797266
Whisper Small Ar - Ibrhm S
This model is a fine-tuned version of Ibrhm-S/arabic-speech-to-text on the arabic-speech-to-text dataset. It achieves the following results on the evaluation set:
- Loss: 3.1640
- Wer: 96.5831
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: 5
- 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0002 | 333.3333 | 1000 | 2.1972 | 94.9886 |
| 0.0001 | 666.6667 | 2000 | 2.7759 | 95.8998 |
| 0.0 | 1000.0 | 3000 | 3.0540 | 95.8998 |
| 0.0 | 1333.3333 | 4000 | 3.1640 | 96.5831 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1