---
library_name: peft
license: apache-2.0
base_model: openai/whisper-small
tags:
- base_model:adapter:openai/whisper-small
- lora
- transformers
datasets:
- generator
metrics:
- wer
model-index:
- name: whisper-es-pr-pe-lora-v7
  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-es-pr-pe-lora-v7

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1256
- Wer: 0.0780

## 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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 1200
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer    |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 1.475         | 0.3333 | 400  | 3.8148          | 2.4353 |
| 0.1218        | 1.0983 | 800  | 0.1386          | 0.0817 |
| 0.0974        | 1.4317 | 1200 | 0.1256          | 0.0780 |


### Framework versions

- PEFT 0.18.0
- Transformers 4.57.2
- Pytorch 2.9.0+cu126
- Datasets 4.4.1
- Tokenizers 0.22.1