Audio record file processing method, apparatus, computer device and storage medium

Abstract

The invention discloses a recording file processing method, which is used for solving the problems that the cleaning operation efficiency of the recording file is low and the arrangement is not standardized easily. The method provided by the invention comprises the following steps: obtaining an uploaded recording file and an original text corresponding to the recording file; invoking a speech recognition interface to perform speech recognition on the recorded file to obtain recognized text; judging whether the recognized text is consistent with the original text; if consistent, the recording file is stored in a preset model training set; if not, the recording file is recorded to the directory to be cleaned, and the recording file recorded in the directory to be cleaned is listened by the processing personnel and fed back to the correct recording text; obtaining the cleaned recording file and the corresponding recording text in the directory to be cleaned; the cleaned recording file andthe corresponding recording text being stored in the model training set. The invention also provides a recording file processing device, a computer device and a storage medium.

Description

technical field [0001] The invention relates to the technical field of voice recognition, in particular to a recording file processing method, device, computer equipment and storage medium. Background technique [0002] At present, speech recognition technology has been widely used, and many platforms have pre-trained speech recognition models, which can provide speech recognition services externally. When the platform trains the speech recognition model, it needs to collect a large number of speech files as samples for the speech recognition model to learn and train. Therefore, many platforms release their own mobile APP clients and encourage users to upload recordings through the APP as training samples. This method can quickly and efficiently collect extremely diverse training samples, but there is also the problem of irregular recording files. Although the recording files collected by the platform are obtained through the original text provided by the platform, and the ...

AI Technical Summary

Problems solved by technology

[0003] At present, the cleaning operation of recording files is manually handled by the processor one by one, which is not only inefficient, but also prone to problems such as irregular arrangement of recording files after cleaning, irregular file directories, etc.

Images