Whisper Tiny It 3 - Gianluca Ruberto
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.711673
- Wer: 43.233500
Model description
This model is the openai whisper small transformer adapted for Italian audio to text transcription. This model has weight decay set to 0.1 to cope with overfitting.
Intended uses & limitations
The model is available through its HuggingFace web app
Training and evaluation data
Data used for training is the initial 10% of train and validation of Italian Common Voice 11.0 from Mozilla Foundation. The dataset used for evaluation is the initial 10% of test of Italian Common Voice. Weight decay showed to have slightly better result also on the evaluation dataset.
Training procedure
After loading the pre trained model, it has been trained on the dataset.
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: 4000
- mixed_precision_training: Native AMP
- weight_decay: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5837 | 0.95 | 1000 | 0.790374 | 50.2981 |
| 0.4183 | 1.91 | 2000 | 0.730100 | 45.4174 |
| 0.3147 | 2.86 | 3000 | 0.713152 | 44.3150 |
| 0.2670 | 3.82 | 4000 | 0.711673 | 43.2335 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 2