metadata
language:
- ar
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Small - Arabic language
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_11_0
type: common_voice_11_0
config: ar
split: test
args: ar
metrics:
- name: Wer
type: wer
value: 46.54301717014048
Whisper Small - Arabic language
This model is a fine-tuned version of MohammadJamalaldeen/whisper-small-with-google-fleurs-ar-4000_steps on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3383
- Wer: 46.5430
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: 8
- 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 |
|---|---|---|---|---|
| 0.347 | 0.2 | 1000 | 0.4275 | 53.6902 |
| 0.2591 | 0.39 | 2000 | 0.3821 | 49.4996 |
| 0.2681 | 0.59 | 3000 | 0.3503 | 47.5989 |
| 0.271 | 0.78 | 4000 | 0.3383 | 46.5430 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.7.0
- Tokenizers 0.13.2