metadata
language:
- ara
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- uoseftalaat/hoping_its_final_dataset
metrics:
- wer
model-index:
- name: Whisper Small for quran recognition
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Quran_requiters
type: uoseftalaat/hoping_its_final_dataset
config: default
split: test
args: 'config: default, split: train'
metrics:
- name: Wer
type: wer
value: 3.3350524325253565
Whisper Small for quran recognition
This model is a fine-tuned version of openai/whisper-small on the Quran_requiters dataset. It achieves the following results on the evaluation set:
- Loss: 0.0178
- Wer: 3.3351
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: 16
- 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: 2000
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.0185 | 1.62 | 500 | 0.0355 | 7.8563 |
0.0012 | 3.24 | 1000 | 0.0224 | 4.4525 |
0.0004 | 4.85 | 1500 | 0.0186 | 3.4554 |
0.0002 | 6.47 | 2000 | 0.0178 | 3.3351 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.1.2
- Datasets 2.17.1
- Tokenizers 0.15.1