metadata

language:
  - ar
license: apache-2.0
base_model: openai/whisper-small
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_17_0
metrics:
  - wer
model-index:
  - name: WhisperArabic
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 17.0
          type: mozilla-foundation/common_voice_17_0
          config: ar
          split: None
          args: ar
        metrics:
          - name: Wer
            type: wer
            value: 115.5525018187697

WhisperArabic

This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.3729
Wer: 115.5525

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: 2500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3354	0.2060	1000	0.4203	94.8333
0.2281	0.4119	2000	0.3729	115.5525

Framework versions

Transformers 4.41.2
Pytorch 2.1.2
Datasets 3.2.0
Tokenizers 0.19.1