zh-CN-model-medium-1 - whucedar

This model is a fine-tuned version of openai/whisper-medium on the zh-CN dataset. It achieves the following results on the evaluation set:

• Loss: 0.1323
• Wer: 188.4793

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: 50
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0241	1.5873	100	0.1363	158.9862
0.0042	3.1746	200	0.1312	239.6313
0.0043	4.7619	300	0.1316	215.2074
0.0013	6.3492	400	0.1312	203.6866
0.0006	7.9365	500	0.1323	188.4793

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.1+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1