---
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-med-LoRA_r256_a512
  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-med-LoRA_r256_a512

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: 0.1651
- Wer: 8.1980

## 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: 5

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Wer     |
|:-------------:|:-----:|:-----:|:---------------:|:-------:|
| 0.4485        | 1.0   | 2801  | 0.2746          | 12.6314 |
| 0.2029        | 2.0   | 5602  | 0.2104          | 9.9943  |
| 0.1503        | 3.0   | 8403  | 0.1869          | 9.2299  |
| 0.119         | 4.0   | 11204 | 0.1729          | 8.5993  |
| 0.0997        | 5.0   | 14005 | 0.1651          | 8.1980  |


### Framework versions

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