---
language:
- fa
license: apache-2.0
base_model: vargha/whisper-large-v3
tags:
- generated_from_trainer
datasets:
- vargha/persian_customer-service_datasets
metrics:
- wer
model-index:
- name: Whisper large V3 Persian-Tuned
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: persian_customer-service
      type: vargha/persian_customer-service_datasets
      args: 'config: fa, split: test'
    metrics:
    - name: Wer
      type: wer
      value: 45.70446735395189
---

<!-- 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 large V3 Persian-Tuned

This model is a fine-tuned version of [vargha/whisper-large-v3](https://huggingface.co/vargha/whisper-large-v3) on the persian_customer-service dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6814
- Wer: 45.7045

## 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: 8
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Wer     |
|:-------------:|:-------:|:----:|:---------------:|:-------:|
| 0.0019        | 23.2558 | 2000 | 0.6164          | 46.6590 |
| 0.0001        | 46.5116 | 4000 | 0.6814          | 45.7045 |


### Framework versions

- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1