uoseftalaat's picture
End of training
37d8ba6 verified
---
language:
- ara
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- AsemBadr/GP
metrics:
- wer
model-index:
- name: Whisper Small for Quran Recognition
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Quran_Reciters
type: AsemBadr/GP
config: default
split: test
args: 'config: default, split: train'
metrics:
- name: Wer
type: wer
value: 3.4381983840467596
---
<!-- 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 Small for Quran Recognition
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Quran_Reciters dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0180
- Wer: 3.4382
## 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
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.0268 | 1.62 | 500 | 0.0316 | 8.0626 |
| 0.002 | 3.24 | 1000 | 0.0205 | 4.3665 |
| 0.0005 | 4.85 | 1500 | 0.0178 | 3.4210 |
| 0.0002 | 6.47 | 2000 | 0.0180 | 3.4382 |
### Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.1.2
- Datasets 2.17.1
- Tokenizers 0.15.2