whisper-zh-CN

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

• Loss: 1.3733
• Wer: 100.0597

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

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0002	76.92	1000	1.1367	99.5818
0.0001	153.85	2000	1.2746	100.0597
0.0001	230.77	3000	1.3383	100.0597
0.0	307.69	4000	1.3733	100.0597

Framework versions

• Transformers 4.32.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.13.1
• Tokenizers 0.13.3