---
language:
- gn
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_16_1
model-index:
- name: Common Voice 16 - Guarani
  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. -->

# Common Voice 16 - Guarani

This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Common Voice 16 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6277
- Cer: 18.8006

## 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: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Cer     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 2.6628        | 0.0573 | 100  | 1.1338          | 24.4276 |
| 1.1592        | 0.1147 | 200  | 0.8507          | 18.6215 |
| 0.9434        | 0.1720 | 300  | 0.7357          | 17.8232 |
| 0.8171        | 0.2294 | 400  | 0.6980          | 16.1916 |
| 0.7444        | 0.2867 | 500  | 0.6277          | 18.8006 |


### Framework versions

- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1