Speech-to-Text Sentiment Analysis Tool

Overview

The Speech-to-Text Sentiment Analysis Tool is a Python-based utility designed for automated sentiment analysis of audio files. Leveraging the power of Vosk for speech recognition and TextBlob for natural language processing, this tool can transcribe audio to text and evaluate the underlying sentiment. Suitable for professionals and researchers in fields like customer service, psychology, and market research, the tool aims to make the process of voice to text conversion and sentiment evaluation both efficient and accurate.

Key Features

• Audio File Support: Compatible with MP3 audio files, automating the conversion process.
• Speech Recognition: Employs the Vosk library to transcribe audio to text.
• Sentiment Analysis: Utilizes TextBlob to assess the sentiment of the transcribed text.
• Data Visualization: Generates a bar chart summarizing the sentiment analysis results.

Technical Requirements

Prerequisites

• Python 3.x
• pip (Python package installer)

Dependencies

• Vosk
• TextBlob
• PyDub
• Matplotlib

Installation and Setup

1. Download Source Code.
2. Change Directory: Navigate to the project folder.

   cd <project-folder>

3. Install Packages: Run the pip command to install the required packages.

   pip install -r requirements.txt

4. Prepare Audio Files: Place your MP3 files in the source folder inside the project directory.
5. Model Configuration: Download the appropriate Vosk model for speech recognition from Vosk Model Zoo and place it in the model folder.
6. Run the Tool: Execute the script.

   python main.py

Usage Guidelines

• On successful execution, the tool will process all MP3 files in the source folder.
• The console will display log messages, including the progress of audio processing, speech-to-text conversion, and sentiment analysis.
• A bar chart will be generated, providing a visual summary of the sentiment scores—categorized as Positive, Negative, or Neutral—for all processed audio files.

By combining speech recognition and sentiment analysis capabilities, the Speech-to-Text Sentiment Analysis Tool offers a comprehensive solution for anyone looking to evaluate the emotional content in audio files.