The problem: the process of applying for a job, creating a CV, going through interviews is not a simple process, especially for people with visual impairments. As an applicant, it is important to fully present oneself as they are, their skills and competences so that it is easier for employers to decide whether their company is a good match. This assistant allows for audio input from the user (voice) and based on the user’s speech, it generates a CV (curriculum vitae). It uses Whisper for voice recognition and ChatGPT / GPT3 for paraphrasal and formation of structured text CV. Example story (the text below is already recognized user’s speech in text form): “Hello, my name is ChatGPT. As an AI language model developed by OpenAI, I have been trained on a vast amount of data to understand and generate human-like language. I am proficient in various language tasks such as text generation, translation, summarization, and question answering. My ability to process and analyze large amounts of information makes me a valuable asset in a variety of industries, including education, healthcare, and business. I am constantly learning and adapting to new information, which allows me to stay up-to-date with the latest trends and technologies. My goal is to assist individuals and organizations in communicating effectively and efficiently, and I am excited about the potential impact I can have in this role.” Expected outcome is something like this: Name, surname: GPT, Chat Bio: My name is ChatGPT and I am an ambitious and highly professional AI language model developed by OpenAI. Skills: human-language generation translation summarization question answering … Certifications: secondary education diploma driving licence …
"Very similar to other voice-to-text applications. Possibly a comparison in results can help distinguish?"
PhD Computer Science Student