---
library_name: peft
license: apache-2.0
base_model: openai/whisper-base
tags:
- base_model:adapter:openai/whisper-base
- lora
- transformers
metrics:
- wer
model-index:
- name: whisper-small-finetuned-multilingual-on-kaggle
  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-small-finetuned-multilingual-on-kaggle

This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6732
- Wer: 191.2033

## 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: 32
- eval_batch_size: 64
- seed: 42
- 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: 500
- training_steps: 5000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Wer      |
|:-------------:|:-------:|:----:|:---------------:|:--------:|
| No log        | 0       | 0    | 2.0460          | 162.1874 |
| 0.3398        | 2.2523  | 1000 | 1.8079          | 181.3942 |
| 0.3015        | 4.5045  | 2000 | 1.7287          | 176.3787 |
| 0.2972        | 6.7568  | 3000 | 1.6952          | 184.4728 |
| 0.2783        | 9.0090  | 4000 | 1.6783          | 183.3356 |
| 0.2877        | 11.2613 | 5000 | 1.6732          | 191.2033 |


### Framework versions

- PEFT 0.17.1
- Transformers 4.56.1
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.22.0