---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-medium-loz
  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-loz

This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0237
- Wer: 38.4907

## 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-05
- 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.2252        | 3.11  | 500  | 1.6491          | 50.4707 |
| 0.0815        | 6.21  | 1000 | 1.8170          | 48.7246 |
| 0.0417        | 9.32  | 1500 | 1.8765          | 43.2129 |
| 0.0218        | 12.42 | 2000 | 1.8995          | 40.6316 |
| 0.0062        | 15.53 | 2500 | 1.9751          | 38.6578 |
| 0.0024        | 18.63 | 3000 | 2.0062          | 38.5667 |
| 0.0001        | 21.74 | 3500 | 2.0141          | 38.6274 |
| 0.0001        | 24.84 | 4000 | 2.0237          | 38.4907 |


### Framework versions

- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2