---
library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: whisper-small-es-ja
  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-es-ja

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: 1.1884
- Bleu: 19.9880

## 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: 16
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 32
- total_eval_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- training_steps: 1500
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Bleu    |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 1.4562        | 0.7911 | 250  | 1.4257          | 13.1050 |
| 1.1315        | 1.5823 | 500  | 1.2744          | 16.8159 |
| 0.9172        | 2.3734 | 750  | 1.2167          | 18.6278 |
| 0.7598        | 3.1646 | 1000 | 1.1958          | 20.1775 |
| 0.7627        | 3.9557 | 1250 | 1.1817          | 20.0966 |
| 0.6803        | 4.7468 | 1500 | 1.1884          | 19.9880 |


### Framework versions

- Transformers 4.47.1
- Pytorch 2.4.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0