---
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- google/fleurs
metrics:
- wer
model-index:
- name: Whisper Small Pashto
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: google/fleurs ps_af
      type: google/fleurs
      config: ps_af
      split: test
      args: ps_af
    metrics:
    - name: Wer
      type: wer
      value: 89.14951573849879
---

<!-- 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 Pashto

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the google/fleurs ps_af dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3860
- Wer: 89.1495

## 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: 3e-07
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- 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: 10
- training_steps: 400
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer      |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.9754        | 14.29 | 100  | 1.9261          | 240.8596 |
| 1.5323        | 28.57 | 200  | 1.5718          | 168.5608 |
| 1.338         | 42.86 | 300  | 1.4249          | 96.6480  |
| 1.282         | 57.14 | 400  | 1.3860          | 89.1495  |


### Framework versions

- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2