README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
base_model: openai/whisper-small
model-index:
  - name: arazn-whisper-small-v2
    results: []
datasets:
  - ahmedheakl/arzen-llm-speech-ds
language:
  - en
  - ar
metrics:
  - bleu
  - cer
  - wer
library_name: transformers
pipeline_tag: automatic-speech-recognition

Model Card for Model ID

Please see paper & code for more information:

• https://github.com/ahmedheakl/arazn-llm
• https://arxiv.org/abs/2406.18120

Citation

BibTeX:

@article{heakl2024arzen,
  title={ArzEn-LLM: Code-Switched Egyptian Arabic-English Translation and Speech Recognition Using LLMs},
  author={Heakl, Ahmed and Zaghloul, Youssef and Ali, Mennatullah and Hossam, Rania and Gomaa, Walid},
  journal={arXiv preprint arXiv:2406.18120},
  year={2024}
}

Model Card Authors

• Email: ahmed.heakl@ejust.edu.eg
• Linkedin: https://linkedin.com/in/ahmed-heakl

arazn-whisper-small-v2

This model is a fine-tuned version of openai/whisper-small on the None dataset.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 1
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2