增强现实AR>> PSTT>> 返回
项目作者： iamarchisha

项目描述 ：
Python Speech to Text
高级语言： JavaScript
项目地址: git://github.com/iamarchisha/PSTT.git
创建时间： 2020-09-19T12:23:26Z
项目社区：https://github.com/iamarchisha/PSTT
开源协议：Apache License 2.0
下载


PSTT- Python Speech to Text

A web application built using Flask.

Features

  1. Speech to Text Transcription:

    • Upload option- a button to upload audio file & perform transcription along with displaying it on the same page.
    • Microphone option- a button to record audio & perform transcription along with displaying it on the same page.
      1. Number of filler words displayed as a count from the transcribed text.
      2. Energy graph of the audio file.

    Implementation

    PyAudio and SpeechRecognition are the two main APIs used for implementation. WebAudioRecorder.js is a JavaScript library that is used here to record audio input (Web Audio API AudioNode object) and encode to audio file image (Blob object).

    Sample audio files are present in wavFiles

    After installing the requirements, in the terminal use: python -m flask run to run the application.

    The web application looks like this: