metadata

language:
  - ar
license: apache-2.0
base_model: openai/whisper-small
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - whitefox123/tashkeel
metrics:
  - wer
model-index:
  - name: Whisper small - tuned
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: CLARtts
          type: whitefox123/tashkeel
          config: default
          split: None
          args: 'config: ar, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 24.36036036036036

Whisper small - tuned

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

Loss: 0.1638
Wer: 24.3604

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: 3125
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1186	1.6	1000	0.1555	26.6667
0.0374	3.2	2000	0.1500	24.3964
0.0222	4.8	3000	0.1638	24.3604

Framework versions

Transformers 4.38.0.dev0
Pytorch 2.1.0+cu118
Datasets 2.17.0
Tokenizers 0.15.2