whisper-tiny-no-specific-topic-v2

This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0124
• Wer: 41.8818

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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4418	4.023	1000	0.7710	46.9364
0.1279	8.046	2000	0.8900	47.7000
0.025	13.0122	3000	0.9975	43.1818
0.0049	17.0353	4000	1.0124	41.8818

Framework versions

• Transformers 4.50.0
• Pytorch 2.5.1+cu121
• Datasets 3.4.1
• Tokenizers 0.21.0