---
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-ar2
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# whisper-largelora-ar2

This model is a fine-tuned version of [openai/whisper-large](https://huggingface.co/openai/whisper-large) on the common_voice_16_1 dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0594
- Wer Ortho: 52.0723
- Wer: 53.1027

## 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: 4
- eval_batch_size: 5
- 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: 3
- training_steps: 40
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer Ortho | Wer     |
|:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
| 1.6294        | 0.2133 | 40   | 2.0594          | 52.0723   | 53.1027 |


### 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