---
language:
- ps_af
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- google/fleurs
metrics:
- wer
model-index:
- name: Whisper Base Pashto - Augmented
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: google/fleurs
      type: google/fleurs
      config: ps_af
      split: test
      args: ps_af
    metrics:
    - name: Wer
      type: wer
      value: 75.59019370460048
---

<!-- 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 Pashto - Augmented

This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the google/fleurs dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1695
- Wer: 75.5902
- Cer: 32.7613

## 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-06
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 30
- training_steps: 600
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer      | Cer      |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
| 2.4594        | 2.38  | 100  | 2.0072          | 337.3411 | 342.0691 |
| 1.8517        | 4.75  | 200  | 1.4907          | 89.7927  | 40.2811  |
| 1.7019        | 7.14  | 300  | 1.3038          | 81.7494  | 36.1352  |
| 1.5249        | 9.52  | 400  | 1.2200          | 77.5575  | 33.8324  |
| 1.4583        | 11.89 | 500  | 1.1808          | 76.5814  | 33.1807  |
| 1.4388        | 14.28 | 600  | 1.1695          | 75.5902  | 32.7613  |


### Framework versions

- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2