Speech-to-text-tenac/STT

A speech to text implementation for the Amharic and Swahili languages # African language Speech Recognition - Speech-to-Text This project demonstartes how to build speech-to-text deep learning model that process and convert African language((Amharic/Swahili) in to text. ## Content - African language Speech Recognition - Speech-to-Text - Content - Introduction - Objective - Data & Features - Usage - Docker-compose - Project Structure - .dvc - Images - data - notebooks - scripts - root directory - contributors ## Introduction The World Food Program wants to deploy an intelligent form that collects nutritional information of food bought and sold at markets in two different countries in Africa - Ethiopia and Kenya. The design of this intelligent form requires selected people to install an app on their mobile phone, and whenever they buy food, they use their voice to activate the app to register the list of items they just bought in their own language. The intelligent systems in the app are expected to live to transcribe the speech-to-text and organize the information in an easy-to-process way in a database. Here we will build a deep learning model that is capable of transcribing a speech to text in the Amharic language. The model we produce will be accurate and is robust against background noise. ## Objective To build a deep learning model that is capable of transcribing a speech to text. ## Data & Features Dataset for: Amharic Swahili Input features (X): audio clips of spoken words Target labels (y): a text transcript of what was spoken ## Usage ### Docker-compose Both the front-end and the back-end could be run on a docker container. **1. Clone the repo** ``` git clone github.com ``` **2. cd into repo** ``` cd STT ``` **3.Start docker container:** ``` docker-compose up -d ``` ## Project Structure ### .dvc used to track large files, models, dataset directories. ### Images a directory for images and results ### data a directory to hold versioned datasets ### notebooks a directory f …