---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-synthesized-turkish-2-hour-llr
  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-synthesized-turkish-2-hour-llr

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3951
- Wer: 19.9165

## 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-06
- 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: 500
- training_steps: 1000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 1.8628        | 2.08  | 100  | 1.5674          | 43.7709 |
| 1.2263        | 4.17  | 200  | 0.8646          | 92.1838 |
| 0.6358        | 6.25  | 300  | 0.6243          | 85.3580 |
| 0.4969        | 8.33  | 400  | 0.5477          | 92.8998 |
| 0.3972        | 10.42 | 500  | 0.4908          | 55.3938 |
| 0.318         | 12.5  | 600  | 0.4504          | 30.9785 |
| 0.2689        | 14.58 | 700  | 0.4256          | 24.1289 |
| 0.2193        | 16.67 | 800  | 0.4094          | 20.2387 |
| 0.2067        | 18.75 | 900  | 0.3988          | 19.8926 |
| 0.1861        | 20.83 | 1000 | 0.3951          | 19.9165 |


### Framework versions

- Transformers 4.29.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3