mtkresearch
Popular repositories Loading
-
-
generative-fusion-decoding
generative-fusion-decoding PublicGenerative Fusion Decoding (GFD) is a novel framework for integrating Large Language Models (LLMs) into multi-modal text recognition systems like ASR and OCR, improving performance and efficiency b…
-
TASTE-SpokenLM
TASTE-SpokenLM PublicA method that directly addresses the modality gap by aligning speech token with the corresponding text transcription during the tokenization stage.
-
function-calling-leaderboard-for-zhtw
function-calling-leaderboard-for-zhtw PublicFunction Calling Leaderboard for Traditional Chinese (zh-tw)
Repositories
- BreezeApp Public
BreezeAPP 是一款為 Android 和 iOS 平台開發的純手機 AI 應用程式。從 App Store下載，即可在不連網的狀態下享受多項 AI 功能。源碼由聯發創新基地(MediaTek Research)提供。我們旨在推廣兩個概念: 人人都可以在自己的手機上自由選擇並運行不同的LLM - one is free to choose one's own LLM to run on a phone，以及任何app開發者都可以輕鬆寫作創意的純手機AI應用 - any dev can create purely phone-based AI apps easily。
mtkresearch/BreezeApp’s past year of commit activity - TASTE-SpokenLM Public
A method that directly addresses the modality gap by aligning speech token with the corresponding text transcription during the tokenization stage.
mtkresearch/TASTE-SpokenLM’s past year of commit activity - Breeze-ASR-25 Public
Breeze ASR 25 是一款先進的自動語音辨識（ASR）模型，基於 Whisper-large-v2 微調而成，特別針對台灣華語以及華語與英語混用的情境進行優化。Breeze ASR 25 is an advanced ASR model fine-tuned from Whisper-large-v2, optimized for Taiwanese Mandarin and Mandarin-English code-switching scenarios.
mtkresearch/Breeze-ASR-25’s past year of commit activity - BreezyVoice Public
mtkresearch/BreezyVoice’s past year of commit activity - symo_notebooks Public
mtkresearch/symo_notebooks’s past year of commit activity - Roo-Code Public
mtkresearch/Roo-Code’s past year of commit activity - generative-fusion-decoding Public
Generative Fusion Decoding (GFD) is a novel framework for integrating Large Language Models (LLMs) into multi-modal text recognition systems like ASR and OCR, improving performance and efficiency by enabling seamless fusion without requiring re-training.
mtkresearch/generative-fusion-decoding’s past year of commit activity - TASTE-SpokenLM.github.io Public
mtkresearch/TASTE-SpokenLM.github.io’s past year of commit activity - latent-flow-transformer Public
mtkresearch/latent-flow-transformer’s past year of commit activity
Most used topics
Loading…