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: 0.1456
- Wer: 5.4805
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
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1951 | 0.2 | 1000 | 0.1851 | 7.6268 |
| 0.1311 | 0.4 | 2000 | 0.1565 | 6.2885 |
| 0.0681 | 1.12 | 3000 | 0.1555 | 6.0394 |
| 0.067 | 1.32 | 4000 | 0.1470 | 5.6148 |
| 0.0336 | 2.05 | 5000 | 0.1456 | 5.4805 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 6
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-2
Space using EdoAbati/whisper-medium-it-2 1
Evaluation results
- Wer on mozilla-foundation/common_voice_11_0 ittest set self-reported5.481