Coders Packet

Voice to Text using deepspeech api in Python

By Divya Prackash Ravi

  • sample.wav
  • deep.py
  • result.png
  • We will be using deepspeech in this python code to generate the text from a voice. Deepspeech is an open-source api for Speech to text.

    DeepSpeech is an open-source Speech-To-Text engine, using a model trained machine learning techniques based on Baidu’s Deep Speech research paper.

    To install the required package sue the following commands

    pip install deepspeech==0.9.3 (DeepSpeech only works with python version 3.7 and lower)

    wget https://github.com/mozilla/DeepSpeech/releases/download/v0.9.3/deepspeech-0.9.3-models.pbmm (to download the acoustic model)
    wget https://github.com/mozilla/DeepSpeech/releases/download/v0.9.3/deepspeech-0.9.3-models.scorer (to download the language model)
     
     
     

     

     

    Download Complete Code

    Comments

    No comments yet