Speech recognition method and device, equipment and storage medium

The invention provides a speech recognition method, device and equipment and a storage medium, and the method comprises the steps: obtaining a to-be-recognized speech, and recognizing the to-be-recognized speech based on a speech recognition model obtained through pre-training, the speech recognition model being obtained through two stages of training, in the first stage, training is carried out with the aim of enabling the recognition result of the training voice to be consistent with the text marked by the training voice, and in the second stage, training is carried out with the aim of balancing the text unit error rate and semantic acceptability of the voice recognition result of the training voice. Through the voice recognition method provided by the invention, a voice recognition result with relatively high user acceptability can be obtained. 本发明提供了一种语音识别方法、装置、设备及存储介质，其中，方法包括：获取待识别语音，基于预先训练得到的语音识别模型对待识别语音进行识别，其中，语音识别模型通过两个阶段的训练得到，第一阶段以使训练语音的识别结果与训练语音标注的文本一致为目标进行训练，第二阶段以平衡训练语音的语音识别结果的文本单元错误率与语义可接受度为目标进行训练