---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-large-v2-spanish
  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-large-v2-spanish

This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1466
- Wer: 0.0855

## 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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 25000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Wer    |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 0.1908        | 0.03  | 1000  | 0.2235          | 0.1154 |
| 0.1888        | 0.07  | 2000  | 0.2132          | 0.1131 |
| 0.167         | 0.1   | 3000  | 0.2115          | 0.1133 |
| 0.1752        | 0.14  | 4000  | 0.2081          | 0.1146 |
| 0.1656        | 0.17  | 5000  | 0.2002          | 0.1073 |
| 0.1535        | 0.21  | 6000  | 0.1971          | 0.1086 |
| 0.1854        | 0.24  | 7000  | 0.1927          | 0.1048 |
| 0.1722        | 0.28  | 8000  | 0.1889          | 0.1043 |
| 0.166         | 0.31  | 9000  | 0.1850          | 0.1022 |
| 0.1277        | 0.35  | 10000 | 0.1820          | 0.1032 |
| 0.1457        | 0.38  | 11000 | 0.1777          | 0.0998 |
| 0.169         | 0.42  | 12000 | 0.1771          | 0.0982 |
| 0.1612        | 0.45  | 13000 | 0.1724          | 0.0976 |
| 0.1616        | 0.49  | 14000 | 0.1693          | 0.0956 |
| 0.1556        | 0.52  | 15000 | 0.1671          | 0.0942 |
| 0.1448        | 0.56  | 16000 | 0.1646          | 0.0930 |
| 0.117         | 0.59  | 17000 | 0.1613          | 0.0914 |
| 0.1441        | 0.62  | 18000 | 0.1596          | 0.0899 |
| 0.148         | 0.66  | 19000 | 0.1571          | 0.0895 |
| 0.1255        | 0.69  | 20000 | 0.1547          | 0.0874 |
| 0.1479        | 0.73  | 21000 | 0.1525          | 0.0885 |
| 0.1304        | 0.76  | 22000 | 0.1503          | 0.0861 |
| 0.1111        | 0.8   | 23000 | 0.1486          | 0.0867 |
| 0.1337        | 0.83  | 24000 | 0.1472          | 0.0854 |
| 0.1289        | 0.87  | 25000 | 0.1466          | 0.0855 |


### Framework versions

- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2