whisper-base-mixedv1.3

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

• Loss: 0.8720
• Cer: 32.0507

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: 0.0001
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• 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
0.0156	34.19	1000	0.8428	26.7480
0.0004	68.38	2000	0.8710	28.1558
0.0004	102.56	3000	0.8693	31.2529
0.0002	136.75	4000	0.8720	32.0507

Framework versions

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