---
library_name: transformers
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-large-v3-chichewa
  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-v3-chichewa

This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.7213
- Wer: 77.8505

## 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: 32
- 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: 5000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Wer     |
|:-------------:|:-------:|:----:|:---------------:|:-------:|
| 0.6163        | 7.4627  | 1000 | 1.8803          | 79.6019 |
| 0.1102        | 14.9254 | 2000 | 2.2954          | 81.6099 |
| 0.0654        | 22.3881 | 3000 | 2.5129          | 87.0942 |
| 0.0502        | 29.8507 | 4000 | 2.6569          | 77.7621 |
| 0.0482        | 37.3134 | 5000 | 2.7213          | 77.8505 |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.0.1
- Datasets 3.0.0
- Tokenizers 0.19.1