---
library_name: transformers
language:
- en
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
metrics:
- wer
- precision
- recall
- f1
model-index:
- name: ./whisper-base-ea_5hr
  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-base-ea_5hr

This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Afrispeech-200 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7154
- Wer Ortho: 0.2898
- Wer: 0.2319
- Cer: 0.1088
- Precision: 0.8599
- Recall: 0.8590
- F1: 0.8585

## 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: 8
- 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: 50
- training_steps: 500
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer Ortho | Wer    | Cer    | Precision | Recall | F1     |
|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:---------:|:------:|:------:|
| 0.9173        | 0.2364 | 100  | 0.9484          | 0.3210    | 0.2633 | 0.1182 | 0.8389    | 0.8419 | 0.8398 |
| 0.8464        | 0.4728 | 200  | 0.8059          | 0.2924    | 0.2312 | 0.1026 | 0.8519    | 0.8523 | 0.8515 |
| 0.7615        | 0.7092 | 300  | 0.7548          | 0.2925    | 0.2340 | 0.1048 | 0.8557    | 0.8556 | 0.8550 |
| 0.7301        | 0.9456 | 400  | 0.7282          | 0.2877    | 0.2288 | 0.1030 | 0.8603    | 0.8613 | 0.8602 |
| 0.5936        | 1.1820 | 500  | 0.7154          | 0.2898    | 0.2319 | 0.1088 | 0.8599    | 0.8590 | 0.8585 |


### Framework versions

- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1