ASR-Using-Deep-Learning
Automatic Speech Recognition is a technique that processes human speech into readable text, also known as speech-to-text or transcription systems.
Reference of similar project : https://www.analyticsvidhya.com/blog/2022/06/automatic-speech-recognition-using-wav2vec2/
About :
Automatic Speech Recognition (ASR) is an important technology to enable and improve the human-human and human-computer interactions. This technology allows users of information systems to speak entries rather than punching numbers on a keyboard.This field has grown exponentially over the past decade, the ASR systems are used in a wide range of applications extending from finance to healthcare. It is an important research area for human-to-machine communication.
Given the popularity and demand of this technology, here is an attempt to create a simple speech recognition system that takes our voice as input and produces the corresponding text by hearing the input by using Wav2Vec2.0– a-state-of-the-art speech recognition approach by Facebook and Hugging Face model hub.
This project is designed to create a simple speech recognition system via Deep learning approach!
Technologies required :
-
Deep-Learning
-
Hugging Face
-
Wav2Vec2.0 Model
-
Python
System Design :
<img src="https://github.com/PrathuashaKB/ASR-Using-Deep-Learning/blob/main/images/ASR%20simplified%20architecture.png" width="100%">