---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: temp1
  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. -->

# temp1

This model is a fine-tuned version of [hts98/whisper-medium-1113](https://huggingface.co/hts98/whisper-medium-1113) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2595
- Wer: 100.0

## 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: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 30
- training_steps: 200
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer   |
|:-------------:|:-----:|:----:|:---------------:|:-----:|
| 0.2081        | 1.2   | 30   | 0.2595          | 100.0 |
| 0.0803        | 2.4   | 60   | 0.2897          | 100.0 |
| 0.0421        | 3.6   | 90   | 0.3009          | 100.0 |
| 0.0207        | 4.8   | 120  | 0.3233          | 100.0 |
| 0.0091        | 6.0   | 150  | 0.3221          | 100.0 |
| 0.0043        | 7.2   | 180  | 0.3213          | 100.0 |


### Framework versions

- Transformers 4.29.0.dev0
- Pytorch 2.0.0+cu117
- Datasets 2.7.0
- Tokenizers 0.13.3