LeoKuo49/whisper-finetune-all_0823

Whisper-finetune_all

This model is a fine-tuned version of openai/whisper-large-v2 on the Amitabha_all dataset. It achieves the following results on the evaluation set:

• Loss: 0.0002
• Cer: 0.1505

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: 16
• eval_batch_size: 8
• 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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.0581	3.1056	1000	0.0515	6.2281
0.0132	6.2112	2000	0.0075	2.8061
0.0009	9.3168	3000	0.0006	0.3260
0.0001	12.4224	4000	0.0002	0.1505

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1