whisper-large-pt

This model is a fine-tuned version of Rafaelrosendo1/whisper-large-pt on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2494
• Wer: 23.0283

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-08
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• training_steps: 9000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0038	21.4	9000	0.2494	23.0283

Framework versions

• Transformers 4.34.0
• Pytorch 2.3.0+cu121
• Datasets 2.12.0
• Tokenizers 0.14.1