EdoAbati/whisper-small-it

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: 0.2013
• Wer: 9.2693

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
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2851	0.25	1000	0.2604	11.9744
0.1885	0.5	2000	0.2176	10.1358
0.1176	1.15	3000	0.2111	9.5664
0.1256	1.4	4000	0.2013	9.2693

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2