CSY1109/drone_small_en

Drone Small En - Siang Yi

This model is a fine-tuned version of openai/whisper-small on the Common Voice 19.0 dataset. It achieves the following results on the evaluation set:

• Loss: 1.5365
• Wer: 29.3651

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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
0.0	500.0	500	1.3457	26.9841
0.0	1000.0	1000	1.3710	26.9841
0.0	1500.0	1500	1.3774	26.9841
0.0	2000.0	2000	1.3967	28.5714
0.0	2500.0	2500	1.4267	28.5714
0.0	3000.0	3000	1.4544	28.5714
0.0	3500.0	3500	1.4849	29.3651
0.0	4000.0	4000	1.5152	29.3651
0.0	4500.0	4500	1.5297	29.3651
0.0	5000.0	5000	1.5365	29.3651

Framework versions

• Transformers 4.48.3
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0