whisper-small-zh-0210

This model is a fine-tuned version of TsaiYing/whisper-small-zh-sample152 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0000
• Cer: 0.1581

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: 5e-06
• train_batch_size: 2
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.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: 50
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.0105	14.2857	100	0.0015	0.1581
0.0008	28.5714	200	0.0002	0.1581
0.0004	42.8571	300	0.0001	0.1581
0.0003	57.1429	400	0.0001	0.1581
0.0002	71.4286	500	0.0001	0.1581
0.0002	85.7143	600	0.0000	0.1581
0.0002	100.0	700	0.0000	0.1581
0.0002	114.2857	800	0.0000	0.1581
0.0002	128.5714	900	0.0000	0.1581
0.0001	142.8571	1000	0.0000	0.1581

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0