Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
Whisper Small NSC part 2 (500 steps) - Jarrett Er
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1985
- Wer: 10.0719
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: 0.0001
- 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: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5682 | 0.6757 | 100 | 0.5376 | 25.0899 |
| 0.3272 | 1.3514 | 200 | 0.3777 | 18.7050 |
| 0.2341 | 2.0270 | 300 | 0.2660 | 13.8040 |
| 0.1432 | 2.7027 | 400 | 0.2183 | 11.1061 |
| 0.1183 | 3.3784 | 500 | 0.1985 | 10.0719 |
Framework versions
- PEFT 0.14.0
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.2.1.dev0
- Tokenizers 0.20.3
- Downloads last month
- 2
Model tree for Thecoder3281f/whisper-small-hi-commonvoice17-500
Base model
openai/whisper-small