CheeLi03/whisper-tiny-it-puct-combine-8k

Whisper Tiny Italian Combine 8k - Chee Li

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

• Loss: 0.4500
• Wer: 53.9953

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: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 8000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5398	0.0849	1000	0.6208	60.3945
0.4876	0.1699	2000	0.5525	56.4670
0.4505	0.2548	3000	0.5174	53.1158
0.4178	0.3398	4000	0.4916	52.5323
0.4058	0.4247	5000	0.4736	51.7368
0.3871	0.5097	6000	0.4621	52.8128
0.3736	0.5946	7000	0.4533	53.4402
0.3844	0.6796	8000	0.4500	53.9953

Framework versions

• Transformers 4.46.2
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.20.1