LeoKuo49/whisper-large-v2

Whisper largev2 amitabha

This model is a fine-tuned version of openai/whisper-large_v2 on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0000
• Cer: 3.0142

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
0.0121	9.1743	1000	0.0062	4.9920
0.0002	18.3486	2000	0.0002	3.0260
0.0	27.5229	3000	0.0001	3.0142
0.0001	36.6972	4000	0.0000	3.0142

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1