---
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: yt-special-batch12-lr4-small-halfcleantest
  results: []
---

<!-- 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. -->

# yt-special-batch12-lr4-small-halfcleantest

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5437
- Wer: 28.2250

## 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: 0.0001
- train_batch_size: 12
- eval_batch_size: 6
- 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: 5000

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 1.363         | 0.26  | 1000 | 1.1114          | 85.9477 |
| 1.0764        | 0.52  | 2000 | 0.8777          | 63.4761 |
| 0.9416        | 0.77  | 3000 | 0.6950          | 43.3953 |
| 0.4797        | 1.03  | 4000 | 0.5948          | 34.7867 |
| 0.4025        | 1.29  | 5000 | 0.5437          | 28.2250 |


### Framework versions

- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3