Whisper Small Italian
This model is a fine-tuned version of openai/whisper-small on the type: common_voice_11_0, name: Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2447
- Wer: 56.4799
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
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.8509 | 0.13 | 100 | 0.8546 | 164.0451 |
| 0.4916 | 0.26 | 200 | 0.5683 | 119.5052 |
| 0.2073 | 0.39 | 300 | 0.2744 | 41.9652 |
| 0.1948 | 0.52 | 400 | 0.2681 | 62.8181 |
| 0.182 | 0.65 | 500 | 0.2678 | 51.2139 |
| 0.1658 | 0.78 | 600 | 0.2526 | 59.0466 |
| 0.1684 | 0.91 | 700 | 0.2447 | 56.4799 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.1
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 7
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 matteocirca/whisper-small-it
Base model
openai/whisper-small