A text recognition method, a text recognition apparatus, an electronic device, and a storage medium are provided. The method includes: extracting character prediction regions of a text line image using a constructed text recognition model, to obtain a character region set; calculating horizon-distance IOUs between the character prediction regions in the character region set according to a position of each character prediction region in the character region set; removing overlapped character prediction regions from the character region set, according to the horizon-distance IOUs between the character prediction regions in the character region set, to obtain a character position set; and sorting and outputting character categories corresponding to the character prediction regions in the character position set according to positions of the character prediction regions in the character position set.