whisper-base-mixedv1.2

This model was trained from scratch on the audiofolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.8069
• Cer: 24.0732

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.0006	66.67	1000	0.7766	25.2933
0.0003	133.33	2000	0.7922	23.7916
0.0001	200.0	3000	0.8016	23.8386
0.0001	266.67	4000	0.8069	24.0732

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.1.1
• Datasets 2.15.0
• Tokenizers 0.15.0