---
title: Eloquent
emoji: 👀
colorFrom: blue
colorTo: indigo
sdk: docker
pinned: false
startup_duration_timeout: 1h
license: cc0-1.0
app_port: 7860
---

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

# Eloquent App: A private coach to speaking clearly

## Introduction
Eloquent App is a gradio app written in python. The app has been tested offline on a laptop with specifications:
- CPU: 11th Gen Intel(R) Core(TM) i7-1165G7 @ 2.80GHz
- RAM: 16.0 GB
- GPU: none
- SSD: at least 25GB available space

The app uses ```automatic-speech-recognition``` and ```text-generation``` models through HuggingFace supported libraries. 
The AI models are about 6GB total. They will be downloaded and cached locally when the app is started for the first time. Therefore, network connection is required and it may take 10-15min for the app to start depending on the download speed. 

## How to run the app on local computer
Clone from the GitLab repository:
```bash
git clone https://gitlab.com/vgotcheva/eloquent-gitlab.git
```

Then go in the cloned folder ```cd eloquent``` and install python dependencies:
```
pip install --no-cache-dir --upgrade -r requirements.txt
```

Run the app.py with python:
```
python app.py
```

## How to run the app in docker on local computer
You will need docker and docker compose installed and started on your local computer. [Get Docker](https://docs.docker.com/get-docker/)

Go in the cloned folder ```cd eloquent``` and run docker compose:
```
docker compose up -d
```
The above command will build the image when it is executed for the first time and then start a docker container with image.

Verify that the image is created and container running
```
docker image ls
docker ps
```

## How to use the app:
Use the app by opening it in your browser:
http://0.0.0.0:7860

## Development Environment
For notes on setting a development environment read [DEVELOPMENT.md](DEVELOPMENT.md)