metadata
library_name: transformers
language:
- tr
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
metrics:
- wer
model-index:
- name: whisper small tr test
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 17.0
type: mozilla-foundation/common_voice_17_0
config: tr
split: None
args: 'config: tr, split: test'
metrics:
- name: Wer
type: wer
value: 20.4853955547986
whisper small tr test
This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2394
- Wer: 20.4854
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: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1898 | 0.6892 | 500 | 0.2532 | 22.0318 |
| 0.1037 | 1.3777 | 1000 | 0.2420 | 20.7698 |
| 0.0658 | 2.0662 | 1500 | 0.2383 | 20.3185 |
| 0.0622 | 2.7553 | 2000 | 0.2394 | 20.4854 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.2