Skip to content

bhautik-pithadiya/speech-to-text

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

40 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Installation Guide

Follow these steps to set up your environment and install the necessary packages for this project.


1. Create a Virtual Environment

To keep dependencies isolated, create a Python virtual environment:

python3 -m venv <env_name>

Activate the environment:

  • On Linux/Mac:
    source <env_name>/bin/activate
  • On Windows:
    <env_name>\Scripts\activate

2. Upgrade pip

Ensure you have the latest version of pip:

pip install --upgrade pip

3. Install Required Packages

3.1. Install NeMo Toolkit

Install a specific version of the NVIDIA NeMo toolkit:

python -m pip install git+https://github.com/NVIDIA/NeMo.git@52d50e9e09a3e636d60535fd9882f3b3f32f92ad

3.2. Install WhisperX

Install WhisperX using its GitHub repository:

python -m pip install git+https://github.com/m-bain/whisperx.git

4. Install youtokentome

To install youtokentome, follow these steps:

  1. Install Cython:

    pip install Cython
  2. Upgrade wheel

    pip install wheel --upgrade
  3. Install youtokentome:

    pip install youtokentome

5. Install Remaining Dependencies

Install all other dependencies from the requirements.txt file:

pip install -r requirements.txt

Common Issues

Error:

ImportError: cannot import name 'ModelFilter' from 'huggingface_hub'

This error may occur when importing:

from nemo.collections.asr.models import EncDecMultiTaskModel

Solution:

The issue is due to a version conflict in the nemo-toolkit[all] package. To resolve this, ensure compatible versions of dependent libraries are installed. Check for updates or compatibility in the nemo-toolkit documentation.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 94.2%
  • CSS 2.4%
  • JavaScript 2.3%
  • Other 1.1%