Open liubin3702 opened 4 years ago
Firstly, you should have an acoustic model. Actually, the Athena-Team project have already provide completed examples to build an ASR system: from building acoustic model to decode using or not using WFST tecology. Please reference to Athena project in our Athena-Team project or just browse here : https://github.com/athena-team/athena#5-decoding-with-wfst
作者您好: 如果我想在您代码基础上,使用WFST或者Beam-Search完成` 拼音 到 汉字 的解码,我需要做些什么? 例如:首先我要获得每个输入拼音状态下对应字典中汉字的一个概率分布(示例中的score.txt中每个状态的batch=3,6,8,11是什么意思) 然后我还需要为代码提供哪些东西来完成拼音到汉字的解码呢? 望回复