This is an introduction to「SentenceTransformer」, a machine learning model that can be used with ailia SDK. You can easily use this model to create AI applications using ailia SDK as well as many other ready-to-use ailia MODELS. Overview SentenceTransformer was built by fine-tuning the language model BERT in order to output…

This article explains how to use ailia SDK from Visual Studio and C#, making it possible to easily incorporate AI features into applications developed in C#. Download Project Files Samples using ailia SDK from Visual Studio and C# are available on github below. https://github.com/axinc-ai/ailia-csharp Download ailia SDK The DLLs needed for running C# samples can be…

Introducing ailia Tokenizer, a tokenizer for NLP that can be used from Unity or C++, without the need for an Python environment. Overview A tokenizer is an API for converting text into tokens (sequences of symbols) that can be handled by AI models, and for converting tokens back into text. Transformers…

This artcicle explains how to generate images of a specific character in StableDiffusionWebUI, after creating our own LoRA using SdWebUITrainTools and Kohya’sGUI. About StableDiffusionWebUI StableDiffusionWebUI is a framework that allows you to easily generate illustrations on your PC using Stable Diffusion. …

This article explains how to generate images with custom character postures using StableDiffusionWebUI for the image creation, and ControlNet for the constraint management. About StableDiffusion and ControlNet StableDiffusion is an AI model that can generate illustrations from an arbitrary text prompt. …

This is a description of NNAPI (Neural Networks API), a low-level API for using NPUs on Android to enable fast inference of AI models. Overview NNAPI (Neural Networks API) is a low-level API for using NPU (Neural Processing Unit) for Android, similarly to what cuDNN is for NVIDIA GPUs. …

We are pleased to introduce version 1.2.16 of ailia SDK, a cross-platform framework to perform fast AI inference on GPU or CPU. You can find more information about ailia SDK on the official website. FP16 support for Vulkan FP16 mode is now supported when using Vulkan to speed up inference in environments with limited…

This article explains how Whisper can be fine-tuned with a small amount of data set to make domain-specific terminology recognizable. By creating a dataset with Tacotron2 synthesized speech, a Whisper model can be created and recognize technical terms. About Whisper Whisper is a speech recognition model developed by OpenAI able to transcribe…

Whisper, an AI model for speech recognition also uses a language model internally, therefore we can apply some prompt engineering concepts to improve the recognition accuracy of unknown words. Whisper Overview Whisper is a speech recognition model developed by OpenAI, the company behind ChatGPT. Whisper converts the input speech into a feature…