whisper-base-en-emo-v1

This model is a fine-tuned version of openai/whisper-base on the Common Voice 17.0(Emotional Tag) dataset. It achieves the following results on the evaluation set:

• Loss: 0.9660
• Wer: 120.1005

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: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• 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	Wer
0.0074	40.0	1000	0.8128	130.1508
0.0002	80.0	2000	0.9065	114.5729
0.0001	120.0	3000	0.9507	109.0452
0.0001	160.0	4000	0.9660	120.1005

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0