---
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-medium-ft-24000
  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-medium-ft-24000

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: 0.1714
- Wer: 6.9790

## 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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.2548        | 1.0   | 1458 | 0.1422          | 7.2180 |
| 0.0841        | 2.0   | 2916 | 0.1303          | 7.5048 |
| 0.0362        | 3.0   | 4374 | 0.1420          | 6.9790 |
| 0.0131        | 4.0   | 5832 | 0.1491          | 7.2658 |
| 0.004         | 5.0   | 7290 | 0.1654          | 7.2180 |
| 0.0012        | 6.0   | 8748 | 0.1714          | 6.9790 |


### Framework versions

- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3