From 37131fd79dfe8e04f9cbaa1a82ad5d2b4442e103 Mon Sep 17 00:00:00 2001 From: Neko Ayaka Date: Wed, 28 May 2025 18:23:09 +0800 Subject: [PATCH] docs(devlog): rephrases --- .../content/docs/blog/DevLog-2025.05.16.mdx | 32 +++++++++++-------- 1 file changed, 19 insertions(+), 13 deletions(-) diff --git a/docs/src/content/docs/blog/DevLog-2025.05.16.mdx b/docs/src/content/docs/blog/DevLog-2025.05.16.mdx index 9fbb413d6..0e9afae3c 100644 --- a/docs/src/content/docs/blog/DevLog-2025.05.16.mdx +++ b/docs/src/content/docs/blog/DevLog-2025.05.16.mdx @@ -56,7 +56,7 @@ Most profoundly appreciated to [@LemonNekoGH](https://github.com/LemonNekoGH) an :::note[What is Character Card?] Well, local-first chat applications like [SillyTavern](https://github.com/SillyTavern/SillyTavern) -, [RisuAI](https://risuai.net/) or online services like [JanitorAI](https://janitorai.com/) uses a +, [RisuAI](https://risuai.net/) or online services like [JanitorAI](https://janitorai.com/) uses、 a file contains character's background, personality, and other role-playing essential context for each individual characters. @@ -104,9 +104,10 @@ It's live in our UI component library, you can play around with it: https://airi - Tauri MCP support - Connects AIRI to Android devices -These two was major update and try-out, she wrote another two DevLogs about -these things and shared the technical details behind the scene. -(Valuable for Tauri developers and users I guess.) You can read them here: +These two was major update and try-out, and this part was done by [@LemonNekoGH](https://github.com/LemonNekoGH), +she wrote another two DevLogs about these things and shared the technical +details behind the scene. (Valuable for Tauri developers and users I guess.) +You can read them here: - [Controls Android](./DevLog-2025.04.22.mdx) - [MCP in Tauri](./DevLog-2025.04.28.md) @@ -150,8 +151,11 @@ from ground up and scratch: - [VAD + ASR + LLM Chat](https://github.com/proj-airi/webai-example-realtime-voice-chat/tree/8462ff6bcb83bb278bce5388d588d2e3e3dd6dae/apps/vad-asr-chat) - [VAD + ASR + LLM Chat + TTS](https://github.com/proj-airi/webai-example-realtime-voice-chat/tree/8462ff6bcb83bb278bce5388d588d2e3e3dd6dae/apps/vad-asr-chat-tts) -We discovered a interesting and powerful repository though, called [k2-fsa/sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx), it -supports the 18 tasks of speech processing across macOS, Windows, Linux, Android, +> Hope you could learn some from them. + +During this time, we discovered a interesting and powerful repository though, +called [k2-fsa/sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx), it supports +18 tasks of speech processing across macOS, Windows, Linux, Android, iOS, etc. over 12 languages. Fascinating! So [@luoling](https://github.com/luoling8192) made another small demo for this too: @@ -159,13 +163,13 @@ So [@luoling](https://github.com/luoling8192) made another small demo for this t #### Birth of xsAI 🤗 Transformers.js -This give birth to a new side project called -[xsAI 🤗 Transformers.js](https://github.com/proj-airi/xsai-transformers) -to be able to call the WebGPU powered model inference and serving with workers -while still keep the API compatible to our prior succeeded project called +Because the work we have done for VAD, ASR, Chat, and TTS demos, this gave the +birth of a new side project called [xsAI 🤗 Transformers.js](https://github.com/proj-airi/xsai-transformers) +, enabling the simplicity to call the WebGPU powered model inference and serving with +workers while still keeping the API compatible to our prior succeeded project called [xsAI](https://github.com/moeru-ai/xsai). -We got a playground for that too... play it on https://xsai-transformers.netlify.app +We got a playground for that too... play it on [https://xsai-transformers.netlify.app](https://xsai-transformers.netlify.app). You can install it via npm today! @@ -180,6 +184,8 @@ powered models with one if switch. This brought us a new possibility to be able to experiment and even achieve simple RAG and re-ranking system right in the browser, without the need of any server side code, or even a backend server. + +Oh, Node.js was supported, too! ::: ### Telegram Bot @@ -201,7 +207,7 @@ one for my own. I did some small experiments on integrating a WebGPU powered background remover right in the system, you can play around with it here in -https://airi.moeru.ai/devtools/background-remove . +[https://airi.moeru.ai/devtools/background-remove](https://airi.moeru.ai/devtools/background-remove). ### xsAI & unSpeech @@ -273,7 +279,7 @@ The slides I used to share was this: Demo Day @ Hangzhou The slides itself is purely open sourced, you can play around -it here too: https://talks.ayaka.io/nekoayaka/2025-05-10-airi-how-we-recreated-it/#/1 +it here too: [https://talks.ayaka.io/nekoayaka/2025-05-10-airi-how-we-recreated-it/#/1](https://talks.ayaka.io/nekoayaka/2025-05-10-airi-how-we-recreated-it/#/1) ## Milestones