{"id":20514321,"url":"https://github.com/devashishprasad/virtual-ai-assistant","last_synced_at":"2025-07-13T23:08:46.524Z","repository":{"id":110729560,"uuid":"422979278","full_name":"DevashishPrasad/Virtual-AI-assistant","owner":"DevashishPrasad","description":"This repository contains my Bachelor's degree final year project. It is a Google colab based interactive Virtual Assistant built using open-sourced libraries.","archived":false,"fork":false,"pushed_at":"2021-11-09T05:22:23.000Z","size":21958,"stargazers_count":11,"open_issues_count":0,"forks_count":9,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-03-05T23:15:50.067Z","etag":null,"topics":["chatbot","speech-to-text","text-to-speech"],"latest_commit_sha":null,"homepage":"","language":"HTML","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DevashishPrasad.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-10-30T20:03:12.000Z","updated_at":"2025-03-04T21:58:00.000Z","dependencies_parsed_at":null,"dependency_job_id":"554bd680-2c5b-4bf1-a024-0cee54b20461","html_url":"https://github.com/DevashishPrasad/Virtual-AI-assistant","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/DevashishPrasad/Virtual-AI-assistant","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DevashishPrasad%2FVirtual-AI-assistant","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DevashishPrasad%2FVirtual-AI-assistant/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DevashishPrasad%2FVirtual-AI-assistant/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DevashishPrasad%2FVirtual-AI-assistant/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DevashishPrasad","download_url":"https://codeload.github.com/DevashishPrasad/Virtual-AI-assistant/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DevashishPrasad%2FVirtual-AI-assistant/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265218750,"owners_count":23729528,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["chatbot","speech-to-text","text-to-speech"],"created_at":"2024-11-15T21:15:53.890Z","updated_at":"2025-07-13T23:08:46.498Z","avatar_url":"https://github.com/DevashishPrasad.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Virtual-AI-assistant\n\nThis virtual assistant can hear, think and respond to you. You can ask general queries (in English) about various flights. The virtual assitant will respond appropriately using its knowledge (the database). It also generates the face emoji based animation with voice as an output. It consists of speech recognition (speech to text), closed domain chatbot, speech generation (text to speech) and video rendering.\n\nThe closed domain chatbot is currently trained on the atis_flight dataset and hence it can only answer certain queries related to flights (see Queries section).\n\nFollow How to run section to see this virtual assistant in action. It is super easy to run. The code is fully tested and works perfectly in google colab.\n\n### Main Libraries\n\n- PyTorch\n- SpeechRecognition\n- OpenCV\n- Sqlite3\n\n# System Architecture\n\u003cimg src='assets/sys_arch.png'\u003e\n\n# Sample output\n\nA simple conversation with virtual assistant. Asking queries and getting answers.\n\nhttps://user-images.githubusercontent.com/37477321/139561844-3fd460b3-6946-4506-8162-2ad6586f97b9.mp4\n\n# Queries\nThis virtual assistant was made to help passengers book flights. It has it's own database that has Indian cities, flights and other related details. We use sqlite database maintained in a .db file (\u003ca href='https://github.com/DevashishPrasad/Virtual-AI-assistant/blob/main/code/closed_domain/atis.db'\u003ehere\u003c/a\u003e). Following are some of the entities that are already present in the database. You can use these entities in your queries.\n\nDatabase - \u003cbr\u003e\nCities : Pune, Mumbai, Nagpur, Chennai \u003cbr\u003e\nFlight IDs: 1, 2, 3, 4, 5, 6, 9, 10, 11 \u003cbr\u003e\nFlight companies: Air India, Go Air, King Fisher, Indigo \u003cbr\u003e\nClasses: Business, Economy \u003cbr\u003e\n\nWe will release the full structure of database soon. And, to test the bot you can ask it the following queries -\n\nType 1 - Hello show me flights from \\\u003ccity\\\u003e to \\\u003ccity\\\u003e.\n\nType 2 - Can you give me minimum fare for flights from \\\u003ccity\\\u003e to \\\u003ccity\\\u003e in the \\\u003cclass\\\u003e class\n\nType 3 - Hi can you give me \\\u003cflight company\\\u003e flights from \\\u003ccity\\\u003e to \\\u003ccity\\\u003e\n\nType 4 - Show me details for flight with id \\\u003cflight id\\\u003e\n\nType 5 - Hey how many seats are available for flights from \\\u003ccity\\\u003e to \\\u003ccity\\\u003e\n\nCurrently the bot is trained only on these 5 types of queries and its all possible variations. Use natural language freely to modify your queries. The virtual assistant will help you as long as your intent is within these 5 types.\n\n# How to run\nJust run the 'Virtual_assistant_notebook.ipynb' notebook in the main folder of this repository in Colab. All dependencies, models and related code is in the notebook itself.\n\n1. Start executing all the cells one by one.\n\n2. When you execute the last cell, it will automatically start recording your voice. When this happens you will see a button that says 'Recording' and you have to say your query at this point.\n\n3. After you are done saying your query, you need to click the button to stop the recording.\n\n4. The bot will show the results of your query and generate an animated face video with it's voice.\n\n# Acknowledgements\n\n1. NVIDIA Flowtron - https://github.com/NVIDIA/flowtron\n2. Joint BERT - https://github.com/monologg/JointBERT\n3. Speech Recognition python library - https://github.com/Uberi/speech_recognition\n  \nVirtual-AI-assistant was made possible because of the repositories mentioned above!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdevashishprasad%2Fvirtual-ai-assistant","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdevashishprasad%2Fvirtual-ai-assistant","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdevashishprasad%2Fvirtual-ai-assistant/lists"}