TheRains/yt-special-batch12-lr4-augment-small

Whisper Small Indonesian

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

• Loss: 0.7352
• Wer: 38.8950

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: 0.0001
• train_batch_size: 12
• eval_batch_size: 6
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.296	0.13	1000	1.3286	110.0123
1.1522	0.26	2000	1.0917	81.6354
1.0175	0.39	3000	0.9399	60.1258
0.7844	0.52	4000	0.8174	43.4862
0.5919	0.64	5000	0.7352	38.8950

Framework versions

• Transformers 4.31.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.13.1
• Tokenizers 0.13.3