SenseVoiceSmall微调模型

对SenseVoiceSmall开源模型用粤语和四川话数据集进行微调,得到微调后的模型。

微调后测试cer

带符号 去符号
微调前 0.35151298237809847 0.19419020076531499
微调后 0.17646826424209877 0.12941482715620842

微调所用数据集

ChenChenyu/VoiceDataSet

Downloads last month
13
Inference API
Unable to determine this model's library. Check the docs .

Model tree for ChenChenyu/SenseVoiceSmall-finetuned

Finetuned
(1)
this model

Dataset used to train ChenChenyu/SenseVoiceSmall-finetuned