---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
base_model: openai/whisper-small
model-index:
- name: whisper_tuning_2
  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_tuning_2

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: 3.8171
- Wer: 22.0048

## 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: 5e-07
- 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: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 4.9019        | 0.2   | 10   | 4.7994          | 22.8435 |
| 4.8102        | 0.4   | 20   | 4.3818          | 22.7236 |
| 4.1548        | 0.6   | 30   | 4.0237          | 22.4042 |
| 4.0853        | 0.8   | 40   | 3.8926          | 22.1246 |
| 3.6087        | 1.0   | 50   | 3.8171          | 22.0048 |


### Framework versions

- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1