---
license: apache-2.0
base_model: openai/whisper-small
tags:
- whisper-event
- generated_from_trainer
datasets:
- google/fleurs
metrics:
- wer
model-index:
- name: Whisper small shona
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: google/fleurs sn_zw
      type: google/fleurs
      config: sn_zw
      split: test
      args: sn_zw
    metrics:
    - name: Wer
      type: wer
      value: 45.9
---

<!-- 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 shona

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the google/fleurs sn_zw dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9653
- Wer: 45.9

## 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: 8
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.09          | 8.16  | 400  | 0.8572          | 50.6875 |
| 0.0019        | 16.33 | 800  | 0.9069          | 46.4438 |
| 0.0008        | 24.49 | 1200 | 0.9473          | 46.0438 |
| 0.0006        | 32.65 | 1600 | 0.9653          | 45.9    |
| 0.0005        | 40.82 | 2000 | 0.9720          | 45.9438 |


### Framework versions

- Transformers 4.37.1
- Pytorch 1.12.0+cu102
- Datasets 2.16.1
- Tokenizers 0.15.1