---
library_name: peft
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-model-small-ro-finetune-5k-05-25
  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-model-small-ro-finetune-5k-05-25

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0985
- Wer: 0.4624
- Cer: 0.2841

## 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: 2e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 30
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
| 3.6753        | 1.0   | 82   | 1.7550          | 0.8743 | 0.5767 |
| 1.5041        | 2.0   | 164  | 1.2064          | 0.9738 | 0.9931 |
| 1.353         | 3.0   | 246  | 1.1390          | 0.7133 | 0.5702 |
| 1.2802        | 4.0   | 328  | 1.1080          | 0.5619 | 0.3729 |
| 1.2578        | 5.0   | 410  | 1.0985          | 0.4624 | 0.2841 |


### Framework versions

- PEFT 0.15.2
- Transformers 4.52.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1