iqbalasrif/whisper-tiny-finetuned

finetune

This model is a fine-tuned version of openai/whisper-tiny.en on the lalipa/jv_id_asr_split jv_id_asr_source dataset. It achieves the following results on the evaluation set:

• Loss: 1.7784
• Wer: 0.7836
• Cer: 0.2535

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: 32
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• 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: 30
• training_steps: 150

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
3.6903	0.2041	30	2.9875	1.0127	0.4365
2.533	0.4082	60	2.2360	0.8879	0.2921
2.0604	0.6122	90	1.9514	0.8253	0.2670
1.852	0.8163	120	1.8182	0.7949	0.2581
1.7929	1.0204	150	1.7784	0.7836	0.2535

Framework versions

• Transformers 4.46.0.dev0
• Pytorch 2.4.1
• Datasets 3.0.1
• Tokenizers 0.20.0