https://github.com/praveendecode/speech_to_text_conversion
Python-based Speech-to-Text Conversion : converting live voice into text
https://github.com/praveendecode/speech_to_text_conversion
Last synced: 29 days ago
JSON representation
Python-based Speech-to-Text Conversion : converting live voice into text
- Host: GitHub
- URL: https://github.com/praveendecode/speech_to_text_conversion
- Owner: praveendecode
- Created: 2023-09-12T10:09:25.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2023-09-12T12:46:50.000Z (over 1 year ago)
- Last Synced: 2025-02-09T13:35:10.952Z (3 months ago)
- Language: Python
- Size: 4.88 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Speech Recognition and Data Analysis Script
This Python script utilizes speech recognition to interactively query and analyze data using natural language processing techniques. It incorporates the Googletrans library for speech recognition, PyAudio for
audio input, and PandasAI for data analysis. Additionally, it uses the OpenAI GPT-3.5 language model to provide answers to user queries.
# Prerequisites
pip install googletrans==3.1.0a
pip install SpeechRecognition
pip install PyAudio
pip install pandasai
# Code Process
To use the script, ensure that you have the required dependencies installed and a CSV file named "diabetes.csv" in the script's directory. Run the script using Python, and it will prompt you to speak your
query. After speaking, it will display the recognized text and ask if you want to proceed with the query. Type "5" to proceed or "6" to speak again. Upon proceeding, the script will use PandasAI to analyze
the data and display the results. To stop the script, enter "2" when prompted.
Please note that this script is intended for local use, as it relies on microphone input.
# For Queries Connect Through [LinkedIn](https://www.linkedin.com/in/praveen-n-2b4004223/)