---
language:
- id
license: apache-2.0
base_model: openai/whisper-small
tags:
- id-asr-leaderboard
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper Small ID - norm
  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. -->

# Whisper Small ID - norm

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 5.4712
- Wer: 282.7881

## 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: 8
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer       |
|:-------------:|:-----:|:----:|:---------------:|:---------:|
| 17.6812       | 1.94  | 1000 | 12.3783         | 1360.8144 |
| 6.976         | 3.87  | 2000 | 8.7546          | 241.4815  |
| 2.0938        | 5.81  | 3000 | 7.1760          | 899.5997  |
| 0.3231        | 7.74  | 4000 | 5.4712          | 282.7881  |


### Framework versions

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