metadata

license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: openai/whisper-large
datasets:
  - common_voice_11_0
metrics:
  - wer
model-index:
  - name: whisper-LARGE-AR
    results: []

whisper-LARGE-AR

This model is a fine-tuned version of openai/whisper-large on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

Loss: 0.6586
Wer Ortho: 52.7723
Wer: 56.2992

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: 0.0002
train_batch_size: 4
eval_batch_size: 4
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: constant_with_warmup
lr_scheduler_warmup_steps: 10
training_steps: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.349	0.8	50	0.6586	52.7723	56.2992

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