whisper-tiny-Entertainment-V3

This model is a fine-tuned version of wwwtwwwt/whisper-tiny-no-specific-topic-V3 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7860
• Wer: 37.7403

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: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.6489	0.16	800	0.8086	45.2910
0.6724	1.1532	1600	0.7690	41.5540
0.2709	2.1464	2400	0.7574	41.8305
0.415	3.1396	3200	0.7808	37.7820
0.3518	4.1328	4000	0.7777	38.0255
0.2221	5.126	4800	0.7860	37.7403

Framework versions

• Transformers 4.50.3
• Pytorch 2.5.1+cu121
• Datasets 3.5.0
• Tokenizers 0.21.0