whisper-medium-th-cv12

This model is a fine-tuned version of biodatlab/whisper-medium-th-combined-v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3122
• Wer: 23.0133

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: 6.25e-06
• train_batch_size: 32
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 25
• training_steps: 250
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.8675	0.41	50	0.8984	28.2734
0.2598	0.82	100	0.3498	25.4960
0.1256	1.23	150	0.3226	24.8385
0.1198	1.64	200	0.3162	23.7955
0.1032	2.05	250	0.3122	23.0133

Framework versions

• Transformers 4.30.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.12.1.dev0
• Tokenizers 0.13.3