---
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-variant-b-normalized-transcript
  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-variant-b-normalized-transcript

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: 1.3983
- Wer: 59.3004
- Cer: 28.1383

## 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: 7.5e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.05
- training_steps: 3000

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Wer     | Cer     |
|:-------------:|:-------:|:----:|:---------------:|:-------:|:-------:|
| 6.1874        | 0.9259  | 100  | 1.4766          | 82.4754 | 37.1937 |
| 4.3049        | 1.8519  | 200  | 1.1418          | 74.2396 | 35.4061 |
| 3.2137        | 2.7778  | 300  | 1.0356          | 62.0496 | 28.7776 |
| 2.3819        | 3.7037  | 400  | 1.0180          | 61.5466 | 27.8582 |
| 1.7253        | 4.6296  | 500  | 1.0404          | 61.4998 | 29.3362 |
| 1.2334        | 5.5556  | 600  | 1.1001          | 57.9902 | 27.0954 |
| 0.7779        | 6.4815  | 700  | 1.1463          | 59.2302 | 28.1762 |
| 0.5770        | 7.4074  | 800  | 1.2063          | 57.3701 | 26.3506 |
| 0.3544        | 8.3333  | 900  | 1.2435          | 61.1254 | 28.6804 |
| 0.2340        | 9.2593  | 1000 | 1.3227          | 59.6280 | 28.2108 |
| 0.1444        | 10.1852 | 1100 | 1.3311          | 57.8147 | 26.0277 |
| 0.1176        | 11.1111 | 1200 | 1.3743          | 57.6626 | 26.5121 |
| 0.1288        | 12.0370 | 1300 | 1.3983          | 59.3004 | 28.1383 |


### Framework versions

- Transformers 5.8.1
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.22.2