metadata

license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: openai/whisper-large
datasets:
  - common_voice_16_1
metrics:
  - wer
model-index:
  - name: whisper-largelora-ar
    results: []

whisper-largelora-ar

This model is a fine-tuned version of openai/whisper-large on the common_voice_16_1 dataset. It achieves the following results on the evaluation set:

Loss: 1.3158
Wer Ortho: 49.1826
Wer: 59.3335

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: 5
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 15
training_steps: 157
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.7568	0.8351	157	1.3158	49.1826	59.3335

Framework versions

PEFT 0.11.2.dev0
Transformers 4.42.0.dev0
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1