liyijing024 / transcription-of-audio-video-files-with-speakers-tone-analysis. Goto Github PK

This project forked from agar2995/transcription-of-audio-video-files-with-speakers-tone-analysis.

Taken audio/video files as input and converted to corresponding text files using Google API. Further, the text transcription is used for sentiment (tone) analysis of the speaker using yet another IBM Watson API. The software comes as a web application where in the user can upload the audio/video file to be converted and can download the transcribed file. Along with the transcription, the output file conveys information about the sentiment of the speaker at the sentence level of speech. The team aims at taking this project to a level where the application could live stream the audio/video files without any lag.