Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
Whisper Small hi 2
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3689
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: 0.001
- train_batch_size: 16
- eval_batch_size: 32
- 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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0 | 1 | 2.2900 |
| 0.5292 | 1.22 | 500 | 0.3877 |
| 0.2389 | 2.44 | 1000 | 0.3418 |
| 0.1726 | 3.67 | 1500 | 0.3191 |
| 0.1228 | 4.89 | 2000 | 0.3221 |
| 0.076 | 6.11 | 2500 | 0.3478 |
| 0.0399 | 7.33 | 3000 | 0.3689 |
Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.40.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 5
Model tree for korbih/whisper-small-hi-PEFT_True-8Bit_True-lr_0.001
Base model
openai/whisper-small