cherifkhalifah's picture
Upload processor
4385759 verified
metadata
base_model: openai/whisper-small
datasets:
  - audiofolder
language:
  - ar
library_name: transformers
license: apache-2.0
metrics:
  - wer
tags:
  - generated_from_trainer
model-index:
  - name: quran-whisper-tiny-v1
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: audiofolder
          type: audiofolder
          config: default
          split: train
          args: default
        metrics:
          - type: wer
            value: 3.5864978902953584
            name: Wer

quran-whisper-tiny-v1

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

  • Loss: 0.0329
  • Wer: 3.5865

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: 2000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0154 16.9492 1000 0.0404 3.5865
0.0021 33.8983 2000 0.0329 3.5865

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1