---
library_name: peft
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
metrics:
- wer
- cer
model-index:
- name: whisper-model-small-ro-finetune-5k-50-50
  results: []
datasets:
- victors3136/dataset-5k-50it-50sp
language:
- ro
---

<!-- 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-50-50

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: 1.0462
- Wer: 0.2851
- Cer: 0.0710

## 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    |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
| 2.5278        | 1.0   | 125  | 1.3356          | 0.7715 | 0.8917 |
| 1.5011        | 2.0   | 250  | 1.1585          | 0.5180 | 0.3362 |
| 1.4233        | 3.0   | 375  | 1.0967          | 0.3243 | 0.1098 |
| 1.3585        | 4.0   | 500  | 1.0608          | 0.2867 | 0.0722 |
| 1.3203        | 5.0   | 625  | 1.0462          | 0.2851 | 0.0710 |


### Framework versions

- PEFT 0.15.2
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1