---
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- tutikentuti/quiztest
metrics:
- wer
model-index:
- name: Whisper Tiny Quiztest
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: quiztest
      type: tutikentuti/quiztest
      config: default
      split: None
      args: default
    metrics:
    - name: Wer
      type: wer
      value: 55.05
---

<!-- 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 Tiny Quiztest

This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the quiztest dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0947
- Wer: 55.05

## 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-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 1000
- training_steps: 1000

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer   |
|:-------------:|:-----:|:----:|:---------------:|:-----:|
| 0.7317        | 2.0   | 500  | 0.4655          | 73.0  |
| 0.2146        | 4.0   | 1000 | 0.0947          | 55.05 |


### Framework versions

- Transformers 4.41.0
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1