metadata

library_name: transformers
language:
  - ar
license: apache-2.0
base_model: openai/whisper-Small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_16_1
metrics:
  - wer
model-index:
  - name: Whisper Samll Ar
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 16.1
          type: mozilla-foundation/common_voice_16_1
          config: ar
          split: test
          args: 'config: ar, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 44.497132774591975

Whisper Samll Ar

This model is a fine-tuned version of openai/whisper-Small on the Common Voice 16.1 dataset. It achieves the following results on the evaluation set:

Loss: 0.3402
Wer: 44.4971

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
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
0.3175	0.4122	1000	0.4157	50.2739
0.2705	0.8244	2000	0.3707	49.3769
0.1648	1.2366	3000	0.3512	45.7212
0.1485	1.6488	4000	0.3402	44.4971

Framework versions

Transformers 4.48.3
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0