---
library_name: transformers
language:
- tr
license: apache-2.0
base_model: ysdede/whisper-small-turkish-0
tags:
- generated_from_trainer
model-index:
- name: whisper-small-turkish-0-med-0
  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-small-turkish-0-med-0

This model is a fine-tuned version of [ysdede/whisper-small-turkish-0](https://huggingface.co/ysdede/whisper-small-turkish-0) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1874

## 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-06
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 40000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 0.0762        | 0.05  | 2000  | 0.1591          |
| 0.0659        | 0.1   | 4000  | 0.1452          |
| 0.0585        | 0.15  | 6000  | 0.1431          |
| 0.0483        | 0.2   | 8000  | 0.1431          |
| 0.0373        | 0.25  | 10000 | 0.1448          |
| 0.0349        | 0.3   | 12000 | 0.1464          |
| 0.0294        | 0.35  | 14000 | 0.1526          |
| 0.0231        | 0.4   | 16000 | 0.1545          |
| 0.0216        | 0.45  | 18000 | 0.1577          |
| 0.0183        | 0.5   | 20000 | 0.1617          |
| 0.015         | 0.55  | 22000 | 0.1679          |
| 0.014         | 0.6   | 24000 | 0.1700          |
| 0.0123        | 0.65  | 26000 | 0.1748          |
| 0.0107        | 0.7   | 28000 | 0.1795          |
| 0.0101        | 0.75  | 30000 | 0.1814          |
| 0.0097        | 0.8   | 32000 | 0.1838          |
| 0.0093        | 0.85  | 34000 | 0.1864          |
| 0.0091        | 0.9   | 36000 | 0.1861          |
| 0.0088        | 0.95  | 38000 | 0.1870          |
| 0.0085        | 1.0   | 40000 | 0.1874          |


### Framework versions

- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.20.3