mattiasu96/whisper-tiny-it

Whisper tiny italian - Mattia Surricchio

This model is a fine-tuned version of openai/whisper-tiny on the mozilla-foundation/common_voice_11_0 it dataset. It achieves the following results on the evaluation set:

• Loss: 0.4736
• Wer: 26.4951

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: 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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3889	0.2	1000	0.6844	39.1000
0.5832	0.4	2000	0.5691	31.9995
0.524	0.6	3000	0.4993	28.2672
0.4663	0.8	4000	0.4799	26.7230
0.3107	1.05	5000	0.4736	26.4951

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.12.1+cu113
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2