---
library_name: transformers
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: voice-clone-large-finetune-final
  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. -->

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/neuronbit-tech/finetune_voice_clone_imperative_final/runs/5xtsu8wf)
# voice-clone-large-finetune-final

This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4377
- Wer: 15.3572

## 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: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Wer     |
|:-------------:|:-------:|:----:|:---------------:|:-------:|
| 0.1607        | 0.8460  | 250  | 0.5163          | 25.9413 |
| 0.0598        | 1.6920  | 500  | 0.4849          | 24.8444 |
| 0.0257        | 2.5381  | 750  | 0.4450          | 30.4180 |
| 0.0141        | 3.3841  | 1000 | 0.4369          | 19.3003 |
| 0.0029        | 4.2301  | 1250 | 0.4267          | 16.0095 |
| 0.0015        | 5.0761  | 1500 | 0.4209          | 18.4109 |
| 0.0063        | 5.9222  | 1750 | 0.4259          | 19.3300 |
| 0.0016        | 6.7682  | 2000 | 0.4341          | 17.7587 |
| 0.0009        | 7.6142  | 2250 | 0.4121          | 17.0471 |
| 0.0013        | 8.4602  | 2500 | 0.4199          | 16.3653 |
| 0.0009        | 9.3063  | 2750 | 0.4233          | 16.5135 |
| 0.001         | 10.1523 | 3000 | 0.4237          | 16.0688 |
| 0.0019        | 10.9983 | 3250 | 0.4230          | 16.4542 |
| 0.0014        | 11.8443 | 3500 | 0.4292          | 15.8316 |
| 0.0007        | 12.6904 | 3750 | 0.4291          | 15.8316 |
| 0.0005        | 13.5364 | 4000 | 0.4321          | 15.3869 |
| 0.0009        | 14.3824 | 4250 | 0.4334          | 15.2980 |
| 0.001         | 15.2284 | 4500 | 0.4344          | 15.2980 |
| 0.0           | 16.0745 | 4750 | 0.4372          | 15.3572 |
| 0.0           | 16.9205 | 5000 | 0.4377          | 15.3572 |


### Framework versions

- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3