Whisper Small Italian
This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 it dataset. It achieves the following results on the evaluation set:
- Loss: 0.2517
- Wer: 11.2714
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: 64
- 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
- num_epochs: 2.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2529 | 1.0 | 466 | 0.2758 | 12.4907 |
| 0.1711 | 2.0 | 932 | 0.2517 | 11.2714 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 24
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.
Dataset used to train ALM/whisper-it-small
Evaluation results
- Wer on mozilla-foundation/common_voice_11_0 ittest set self-reported11.271