Whisper Medium Italian
This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common_voice_11_0 it dataset. It achieves the following results on the evaluation set:
- Loss: 0.1804
- Wer: 6.3224
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: 32
- eval_batch_size: 16
- 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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1609 | 1.01 | 1000 | 0.1932 | 7.9271 |
| 0.1529 | 2.02 | 2000 | 0.1799 | 7.2786 |
| 0.0501 | 3.04 | 3000 | 0.1762 | 6.7816 |
| 0.0358 | 4.05 | 4000 | 0.1784 | 6.5184 |
| 0.0305 | 5.06 | 5000 | 0.1804 | 6.3224 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- 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 EdoAbati/whisper-medium-it
Evaluation results
- Wer on mozilla-foundation/common_voice_11_0 ittest set self-reported6.322