metadata
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- recall
- precision
model-index:
- name: whisper-base-finetuned-common_voice
results: []
whisper-base-finetuned-common_voice
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: 0.0001
- Accuracy: 1.0
- F1: 1.0
- Recall: 1.0
- Precision: 1.0
- Mcc: 1.0
- Auc: 1.0
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: 8
- 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_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision | Mcc | Auc |
|---|---|---|---|---|---|---|---|---|---|
| 0.0012 | 1.0 | 200 | 0.0024 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0874 | 2.0 | 400 | 0.1391 | 0.975 | 0.9748 | 0.975 | 0.9773 | 0.9694 | 1.0 |
| 0.0003 | 3.0 | 600 | 0.0003 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0002 | 4.0 | 800 | 0.0002 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0001 | 5.0 | 1000 | 0.0002 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0001 | 6.0 | 1200 | 0.0001 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0001 | 7.0 | 1400 | 0.0001 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0001 | 8.0 | 1600 | 0.0001 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0001 | 9.0 | 1800 | 0.0001 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0001 | 10.0 | 2000 | 0.0001 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1