Splend1d/Zhuan
小篆學習器 learn ancient chinese characters
Repositories
Splend1d/Splend1d.github.io
Splend1d/salmon-plus
Splend1d/Language-Residual-Logits-Lens-Visualization-Delta
Language-Residual-Logits-Lens-Visualization-Delta
Splend1d/whisper-patch-breeze
Robust Speech Recognition via Large-Scale Weak Supervision
Splend1d/Splend1d
Splend1d/Language-Residual-Logits-Lens-Visualization
Splend1d/Language-Residual-Logits-Visualization
Visualization of ASR Model logits for LLM-based an non-LLM-based approaches
Splend1d/BreezyVoice
Splend1d/vlm-inference
Splend1d/T5lephone
Code for T5lephone: Bridging Speech and Text Self-supervised Models for Spoken Language Understanding via Phoneme level T5
Splend1d/wav2vec-u-patch
Repository for "Analyzing the Robustness of Unsupervised Speech Recognition", including patches to wav2vec-u and analysis code
Splend1d/datatrove-zhtw
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Splend1d/wav2vec-u
Splend1d/PPA
Prompt Pool Agent
Splend1d/MR-Models
聯發創新基地（MediaTek Research) 致力於研究基礎模型。我們將研究體現在適合繁體中文使用者的模型上，並在使用權許可的情況下，提供模型給學術界研究或產業界使用。
Splend1d/Tomofun-Challenge-Audio-Classificaiton
This is a repository for Tomofun 狗音辨識 AI 百萬挑戰賽, a audio classification challenge focusing on dog sounds and noises inside the house.
Splend1d/Megatron-DeepSpeed
Ongoing research training transformer language models at scale, including: BERT & GPT-2
Splend1d/XDBERT
Code for ACL 2022 Conference Paper "XDBERT: Distilling Visual Information to BERT from Cross-Modal Systems to Improve Language Understanding"
Splend1d/datasets
TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...
Splend1d/s3prl-ssl
Self-Supervised Speech Pre-training and Representation Learning Toolkit.
Splend1d/2019-CAD-Problem-E-Rectilinear-Polygon-Operations-for-Physical-Design
A C++ code which uses boost library to solve the rectilinear polygon splitting problem
Splend1d/hfDUAL
DUAL with run_squad
Splend1d/DUAL-textless-SQA
Textless (ASR-transcript free) Spoken Question Answering. The official release of NMSQA dataset and the implementation of "DUAL: Textless Spoken Question Answering with Speech Discrete Unit Adaptive Learning" paper.
Splend1d/SpeechMix
Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together
Splend1d/darkchess
Multiple Assignments of the Course : "Theory of Computer Games"
Splend1d/medium-appendix
codes and other refs for posts on medium
Splend1d/voidful
Splend1d/lxmert
PyTorch code for EMNLP 2019 paper "LXMERT: Learning Cross-Modality Encoder Representations from Transformers".
Splend1d/research-contributions
Implementations of recent research prototypes/demonstrations using MONAI.