---
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- lyhourt/clean_4
metrics:
- wer
model-index:
- name: whisper-small-clean_4
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: lyhourt/clean_4
      type: lyhourt/clean_4
    metrics:
    - name: Wer
      type: wer
      value: 11.374407582938389
---

<!-- 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-clean_4

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the lyhourt/clean_4 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0801
- Wer: 11.3744

## 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: 64
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 300
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 0.0466        | 0.3333 | 100  | 0.1170          | 15.9953 |
| 0.2315        | 1.0333 | 200  | 0.0852          | 12.6777 |
| 0.0031        | 1.3667 | 300  | 0.0801          | 11.3744 |


### Framework versions

- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1