whisper-base-v3
This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8131
- Wer: 54.6363
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.0483 | 10.0 | 500 | 2.3813 | 300.7007 |
| 1.4107 | 20.0 | 1000 | 1.0215 | 72.7639 |
| 0.961 | 30.0 | 1500 | 0.8458 | 58.4079 |
| 0.8576 | 40.0 | 2000 | 0.8131 | 54.6363 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.2
- Tokenizers 0.20.1
- Downloads last month
- 45
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 devkyle/base-v3
Base model
openai/whisper-base