uaspeech-withctrl-whisper-lg-3-Dec4

This model is a fine-tuned version of openai/whisper-large-v3 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2429
• Wer: 27.4089

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.8375	0.0146	100	0.3004	29.6029
0.2765	0.0291	200	0.2429	27.4089

Framework versions

• Transformers 4.43.4
• Pytorch 2.4.1
• Datasets 3.0.0
• Tokenizers 0.19.1