---
language:
- en
license: apache-2.0
base_model: openai/whisper-small.en
tags:
- generated_from_trainer
datasets:
- bika5/pfedrax
metrics:
- wer
model-index:
- name: Whisper pfe - bika5
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: pfedrax
      type: bika5/pfedrax
      args: 'config: en, split: test'
    metrics:
    - name: Wer
      type: wer
      value: 92.92035398230088
---

<!-- 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 pfe - bika5

This model is a fine-tuned version of [openai/whisper-small.en](https://huggingface.co/openai/whisper-small.en) on the pfedrax dataset.
It achieves the following results on the evaluation set:
- Loss: 3.6101
- Model Preparation Time: 0.006
- Wer: 92.9204

## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch    | Step | Validation Loss | Model Preparation Time | Wer     |
|:-------------:|:--------:|:----:|:---------------:|:----------------------:|:-------:|
| 0.0001        | 83.3333  | 1000 | 3.5216          | 0.006                  | 92.9204 |
| 0.0           | 166.6667 | 2000 | 3.6101          | 0.006                  | 92.9204 |


### Framework versions

- Transformers 4.43.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1