zowlex's picture
Update README.md
0f95224 verified
|
raw
history blame
2.31 kB
metadata
library_name: transformers
language:
  - ar
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_17_0
metrics:
  - wer
model-index:
  - name: Whisper Small AR
    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: 'config: ar_de, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 44.396092688480046

Whisper Small Arabic

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: 0.3517
  • Wer: 44.3961

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: 8000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.2707 0.4119 1000 0.4188 51.3000
0.2452 0.8237 2000 0.3639 46.1863
0.1613 1.2356 3000 0.3470 44.9194
0.1382 1.6474 4000 0.3398 45.0351
0.1177 2.0593 5000 0.3502 44.5154
0.1206 2.4712 6000 0.3501 44.9781
0.1216 2.8830 7000 0.3423 43.5258
0.072 3.2949 8000 0.3517 44.3961

Framework versions

  • Transformers 4.45.1
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.20.0