impaired-v3-independent-all

This model is a fine-tuned version of openai/whisper-large-v3 on the honzapucalek/impaired_v3_independent_all cs dataset. It achieves the following results on the evaluation set:

• Loss: 1.4531
• Wer: 0.4069

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: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0077	13.99	1000	1.0277	0.3968
0.0008	27.97	2000	1.2058	0.4008
0.0001	41.96	3000	1.3848	0.4069
0.0001	55.94	4000	1.4363	0.3998
0.0001	69.93	5000	1.4531	0.4069

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1