Whisper Small Tr - Enes Akman
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:
- eval_loss: 0.2929
- eval_wer: 23.1615
- eval_runtime: 568.3304
- eval_samples_per_second: 3.519
- eval_steps_per_second: 0.07
- epoch: 3.0
- step: 180
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: 100
- eval_batch_size: 50
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 600
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 76
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Binbariyon/whisper-small-tr
Base model
openai/whisper-small