WafaaFraih
/

whisper-small-egy-ar

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Whisper Small egy-ar 2

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

Loss: 0.7332
Wer Ortho: 51.0380
Wer: 46.4072

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: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 50
training_steps: 500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.7444	0.8432	500	0.7332	51.0380	46.4072

Framework versions

Transformers 4.42.4
Pytorch 2.3.1+cu121
Datasets 2.21.0
Tokenizers 0.19.1

Downloads last month: 0

Safetensors

Model size

242M params

Tensor type

F32

·

Inference API

Unable to determine this model's library. Check the docs .

Model tree for WafaaFraih/whisper-small-egy-ar

Base model

openai/whisper-small

Finetuned

(2150)

this model

Dataset used to train WafaaFraih/whisper-small-egy-ar

Evaluation results

Wer on Darija
self-reported

46.407

View on Papers With Code