---
title: README
emoji: 🐨
colorFrom: gray
colorTo: pink
sdk: static
pinned: false
---

## AI Zero to Hero - Classroom Learning Examples

URL |  Example
----|----
1) https://huggingface.co/spaces/awacke1/Art-from-Text-and-Images|
|Gradio demo that git clones diffusion image model and performs image generation from text prompt with optional input image.
2) https://huggingface.co/spaces/awacke1/Sentence2Paragraph|
|Gradio three model transformers NLP demo generating paragraphs from input sentences using GPT2, GPT-NEO-2.7B, GPT-J-6B large language models
3) https://huggingface.co/spaces/awacke1/Image-Search-Similar|
|Streamlit transformers CLIP demo with embeddings for image semantic search
4) https://huggingface.co/spaces/awacke1/Image2OCR|
|Gradio Image to Optical Character Recognition (OCR) for multiple languages including Chinese, German, Spanish, English, Japanese, Hindi, and Russian
5) https://huggingface.co/spaces/awacke1/Streamlit-ASR-Video|
|Streamlit Real time Automatic Speech Recognition (ASR) from YouTube using Torch, AutoModel and Wav2Vec2
6) https://huggingface.co/spaces/awacke1/ZoomClipToon|
|Gradio ONNX image synthesis model demonstration of image input to cartoon image output
7) https://huggingface.co/spaces/awacke1/AI-Quantum|
|Streamlit Quantum AI example using qiskit, grok, qcengine, quantum gate playground, and quirk circuit demonstrating UI sidebar, multiple page and HTML5
8) https://huggingface.co/spaces/awacke1/AIDocumentUnderstandingOCR|
|AI Layout MV2 Processor for document understanding, token classification and image understanding with pytessarct and detectron2
9) https://huggingface.co/spaces/awacke1/TTS-STT-Blocks|
|Gradio Blocks AI Voice Recognition and Response system with sentiment, understanding sentiment from text and generation of realistic output speech to clarify pronunciation and generate audio that is pleasing to interact with.  AI pipeline allows workflow of Recognize Speech, Classify Sentiment, Save Speech to Text (Personalization), Retrieve Crowdsourced requests and responses, and TTS model variation choices so you can compare performance of multiple models across the 5 AI tasks in the workflow for Speech to Text (STT) and Text to Speech (TTS).
10) https://huggingface.co/spaces/awacke1/GradioBlocksDemo-Transformers|
|AI Text Transformation for automated copy writing based on prompt engineering using GPT2, GPT-NEO-2.7B, GPT-J-6B large language models
11) https://huggingface.co/spaces/awacke1/SentenceToGeneratedVideo|
|Gradio AI Video Generator which obtains semantic search results of image examples and composes a short form video (7 seconds)
[![Gradio AI Video Generator which obtains semantic search results of image examples and composes a short form video]({Lighthouse on the ocean landscape oil painting.png})]({Lighthouse on the ocean landscape oil painting.mp4} "Gradio AI Video Generator")