Unit 5 Ali's exercise
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 13 (Alid) dataset. It achieves the following results on the evaluation set:
- Loss: 0.9533
- Wer Ortho: 223.8248
- Wer: 116.3943
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 550
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.9416 | 1.6287 | 500 | 0.9533 | 223.8248 | 116.3943 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1
- Downloads last month
- 79
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for alidenewade/unit_5_exercise
Base model
openai/whisper-tinyDataset used to train alidenewade/unit_5_exercise
Evaluation results
- Wer on Common Voice 13 (Alid)test set self-reported116.394