This is your work, valued

Shanghai

Zhikang Niu-SII

Elite
@ZhikangNiu

Ph.D. Student, SJTU @X-LANCE & SII @sii-research | Intern @Tencent-Hunyuan @MiniMax-AI @InternLM (Shanghai AILab) @microsoft (MSRA)

encodec-pytorch. unofficial implementation of the High Fidelity Neural Audio Compression

176

Semantic-VAE. [INTERSPEECH 2026 Oral]Official code for "Semantic-VAE: Semantic-Alignment Latent Representation for Better Speech Synthesis"

121

A-DMA. [INTERSPEECH 2025 Oral]Official code for "Accelerating Diffusion-based Text-to-Speech Model Training with Dual Modality Alignment"

67

arxiv_daily. Python

23

NDVQ. [SLT 2024]Official code of "NDVQ: Robust Neural Audio Codec with Normal Distribution-Based Vector Quantization"

13

AI-research-tools. :hammer:AI 方向好用的科研工具

5

F5R-TTS. Official code for "F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimization"

3

SLAM-LLM. Speech, Language, Audio, Music Processing with Large Language Model

2

nlp-speech-2023-winter-learning.

2

ZhikangNiu.

2

awesome-ai-tools. A curated list of Artificial Intelligence Top Tools

2

LLaSA_training. LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis

2

F5-TTS. Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

2

Steel-LLM. Train a 1B LLM with 1T tokens from scratch by personal

1

pre-train-dockerfile. An Intro to set up your Speech Docker environment and debug using VSCode

1

svm_theme_classifier. Python

1

descript-audio-codec. State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

1

personal_misc. Jupyter Notebook

1

Cpp_learning. C++

1

Numpy-Study-Python. Numpy学习

1

faster-git.

1

clip_zip. Jupyter Notebook

1

PyTorch-optimizer-test. Python

1

EnCodec_Trainer. Python

1

MachineLearningCode. Jupyter Notebook

1

SceneClassification. Python

1

stable-audio-tools. Generative models for conditional audio generation

1

stable-codec. A family of state-of-the-art Transformer-based audio codecs for low-bitrate high-quality audio coding.

1

Seg. Python

1

kaggle_vegetable_fruit_cls. Jupyter Notebook

1

minimind. 🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT!🌏 Train a 26M-parameter GPT from scratch in just 2h!

1

link-prediction-based-local-path. Python

1

Data-Structure-Algorithm. C

1