zuazo/whisper-tiny-pt

Whisper Tiny Portuguese

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

• Loss: 0.5191
• Wer: 28.9653

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-06
• train_batch_size: 256
• eval_batch_size: 128
• 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
0.4763	14.08	1000	0.5686	31.3114
0.3784	28.17	2000	0.5350	30.0693
0.3286	42.25	3000	0.5239	29.2413
0.3073	56.34	4000	0.5200	29.4138
0.2971	70.42	5000	0.5191	28.9653

Framework versions

• Transformers 4.37.2
• Pytorch 2.0.1+cu117
• Datasets 2.14.4
• Tokenizers 0.15.1