---
library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- dsfsi-anv/za-african-next-voices
metrics:
- wer
model-index:
- name: Whisper whisper-small zulu multilingual
  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. -->

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/dsfsi/za-next-voices/runs/xq686kko)
# Whisper whisper-small zulu multilingual

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the dsfsi-anv/za-african-next-voices dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4544
- Wer: 36.0631

## 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: 64
- 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: constant_with_warmup
- lr_scheduler_warmup_steps: 75
- training_steps: 500
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 0.5667        | 0.3333 | 250  | 0.5901          | 46.0429 |
| 0.3747        | 1.328  | 500  | 0.4832          | 34.6368 |
| 0.272         | 2.3227 | 750  | 0.4544          | 36.0631 |


### Framework versions

- Transformers 4.52.0
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.4