ZhihCheng/whisper-base-with-motor_zh

Whisper base zh v2

This model is a fine-tuned version of ZhihCheng/whisper-base-zh on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1986
• Wer: 68.75

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: 4
• 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: 25
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0375	0.85	50	0.1724	68.75
0.0164	1.69	100	0.1800	68.75
0.0044	2.54	150	0.1788	68.75
0.0031	3.39	200	0.1927	68.75
0.0009	4.24	250	0.1736	62.5
0.0009	5.08	300	0.1984	75.0
0.0006	5.93	350	0.2019	75.0
0.0005	6.78	400	0.1988	75.0
0.0005	7.63	450	0.1989	68.75
0.0005	8.47	500	0.1986	68.75

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.2.0a0+6a974be
• Datasets 2.16.1
• Tokenizers 0.15.1