README.md

metadata

language:
  - ar
license: apache-2.0
base_model: uaepro/whisper-small-ar-2
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_16_0
metrics:
  - wer
model-index:
  - name: Whisper Small ar - majed test
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 16.0
          type: mozilla-foundation/common_voice_16_0
          config: ar
          split: test
          args: 'config: ar, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 168.22177271055537

Whisper Small ar - majed test

This model is a fine-tuned version of uaepro/whisper-small-ar-2 on the Common Voice 16.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3392
• Wer: 168.2218

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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1459	0.41	1000	0.3714	182.4752
0.1378	0.82	2000	0.3486	177.9993
0.0738	1.24	3000	0.3513	184.2939
0.0855	1.65	4000	0.3392	168.2218

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2
• Datasets 2.16.1
• Tokenizers 0.15.0