CSY1109/drone_sy_tiny_t5_V2

Drone test En - Siang Yi

This model is a fine-tuned version of openai/whisper-tiny on the drone command tsv5V2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.1805
• Wer: 8.1081

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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_ratio: 0.2
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0025	25.0	100	0.2638	13.5135
0.0001	50.0	200	0.2306	8.1081
0.0	75.0	300	0.2026	8.1081
0.0	100.0	400	0.1944	8.1081
0.0	125.0	500	0.1895	8.1081
0.0	150.0	600	0.1861	8.1081
0.0	175.0	700	0.1835	8.1081
0.0	200.0	800	0.1817	8.1081
0.0	225.0	900	0.1807	8.1081
0.0	250.0	1000	0.1805	8.1081

Framework versions

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