whisper-large-v2-italian

This model is a fine-tuned version of openai/whisper-large-v2 on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2397
• Wer Ortho: 0.1538
• Wer: 0.1066

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: 3e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.2182	1.0	979	0.2368	0.1564	0.1070
0.1192	2.0	1958	0.2397	0.1538	0.1066

Framework versions

• Transformers 4.30.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.13.1
• Tokenizers 0.13.3