whisper-small-dv
This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 1.4305
- Wer Ortho: 0.3944
- Wer: 0.3701
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-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 100
- training_steps: 450
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.009 | 112.6154 | 450 | 1.4305 | 0.3944 | 0.3701 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0
- Downloads last month
- 7
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for HaniAI/whisper-small-dv
Base model
openai/whisper-tinyDataset used to train HaniAI/whisper-small-dv
Evaluation results
- Wer on PolyAI/minds14self-reported0.370
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("HaniAI/whisper-small-dv", dtype="auto")