---
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
model-index:
- name: cheonanAddresses_torchmodel_model
  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. -->

# cheonanAddresses_torchmodel_model

This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co./openai/whisper-medium) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0528
- Cer: 1.9329

## 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: 16
- 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: 100
- training_steps: 10000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step  | Validation Loss | Cer     |
|:-------------:|:------:|:-----:|:---------------:|:-------:|
| 0.0767        | 0.3101 | 1000  | 0.0752          | 36.5220 |
| 0.0692        | 0.6202 | 2000  | 0.0718          | 2.2982  |
| 0.0619        | 0.9302 | 3000  | 0.0674          | 2.2475  |
| 0.0579        | 1.2403 | 4000  | 0.0637          | 2.1839  |
| 0.0605        | 1.5504 | 5000  | 0.0630          | 2.1412  |
| 0.0549        | 1.8605 | 6000  | 0.0591          | 2.1101  |
| 0.0502        | 2.1705 | 7000  | 0.0566          | 2.0081  |
| 0.0436        | 2.4806 | 8000  | 0.0558          | 2.0168  |
| 0.0518        | 2.7907 | 9000  | 0.0536          | 1.9705  |
| 0.037         | 3.1008 | 10000 | 0.0528          | 1.9329  |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.2.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1