---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- common_voice_13_0
metrics:
- wer
base_model: openai/whisper-large-v2
model-index:
- name: whisper-large-v2-spanish
  results:
  - task:
      type: automatic-speech-recognition
      name: Automatic Speech Recognition
    dataset:
      name: common_voice_13_0
      type: common_voice_13_0
      config: es
      split: test
      args: es
    metrics:
    - type: wer
      value: 0.09930265529872913
      name: Wer
---

<!-- 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 common_voice_13_0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2414
- Wer Ortho: 0.1439
- Wer: 0.0993

## 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: 3e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- num_epochs: 2

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
| 0.2074        | 1.0   | 1752 | 0.2511          | 0.1628    | 0.1211 |
| 0.1323        | 2.0   | 3504 | 0.2414          | 0.1439    | 0.0993 |


### Framework versions

- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3