Speech recognition method and device, storage medium and equipment

The embodiment of the invention discloses a voice recognition method and device, a storage medium and equipment, and mainly aims to solve the problem of poor voice recognition accuracy in the current voice recognition process. The method comprises the following steps: acquiring voice information, wherein the voice information comprises voices of at least two languages; and recognizing the voice information based on a preset voice recognition model to determine a voice recognition result, the preset voice recognition model comprising at least one independent target decoding module, and the target decoding module being at least based on a decoding module obtained by training a training set comprising an error index identifier. 本申请实施例公开了一种语音识别方法装置、存储介质及设备，主要目的在于解决目前语音识别过程中语音识别的准确性较差的问题。该方法包括：获取语音信息，上述语音信息包括至少两种语种的语音；基于预设语音识别模型对上述语音信息进行识别，以确定语音识别结果，其中，上述预设语音识别模型包括至少一个独立的目标解码模块，上述目标解码模块至少基于包括错误索引标识的训练集训练获得的解码模块。