Blueprints

Train a model for synthetic audio detection

This blueprint guides you through training and using a machine learning model that effectively detects synthetic and modified audio content. It provides step-by-step instructions to ensure users can successfully implement the model in their projects.

Finetune an LLM using Federated AI

This Blueprint demonstrates how to finetune LLMs using federated AI with Flower, enabling collaboration on private datasets without sharing raw data. It allows users to enhance their models while maintaining data privacy.

Transcribe Audio Files with Open-Source Whisper Models

This Blueprint shows you how to transcribe audio files using open-source Whisper models via Speaches, a self-hosted server that mimics the OpenAI Whisper API. It provides a practical solution for users looking to implement transcription capabilities in their applications.

Align text transcriptions in speech-to-text applications

This Blueprint enables you to re-adjust Whisper models to user-predefined texts, improving transcription accuracy for uncommon terms or names. It enhances the usability of speech-to-text applications by allowing for customization based on specific needs.

Convert documents to markdown format

This blueprint guides you to convert unstructured documents to Markdown format using the Docling command-line interface. It simplifies the process of document formatting, making it easier for users to manage and share their content.

LLM Document Parser

This Blueprint provides a locally runnable pipeline for parsing structured data from scanned or digital documents using open-source OCR and LLMs. It allows users to extract valuable information from documents efficiently.

Kokoro

Kokoro is an inference library for the Kokoro model, an open-weight TTS model with 82 million parameters. It delivers comparable quality to larger models while being significantly faster and more cost-efficient, making it suitable for various applications.

OuteTTS

OuteTTS is a package for using OuteTTS text-to-speech models. It provides users with the tools necessary to implement TTS capabilities in their applications, enhancing user interaction through voice.

Gradio

Gradio is an open-source Python package that allows you to quickly build a demo or web application for your machine learning model, API, or any arbitrary Python function. It simplifies the process of sharing your work with others through easy-to-use interfaces.

Streamlit

Streamlit is an open-source Python framework for creating interactive data applications effortlessly. It enables users to build and share data-driven applications with minimal coding, making it accessible for data scientists and developers alike.