whisper-large-v3-turbo-arabic
This model is a fine-tuned version of openai/whisper-large-v3-turbo on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4623
- Wer Ortho: 51.0187
- Wer: 31.1455
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 30
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.3383 | 0.0416 | 100 | 0.4623 | 51.0187 | 31.1455 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0
- Downloads last month
- 121
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for mboushaba/whisper-large-v3-turbo-arabic
Base model
openai/whisper-large-v3
Finetuned
openai/whisper-large-v3-turbo