-
HighRateMOS Public
HighRateMOS is the first non-intrusive MOS prediction model that explicitly models sampling rates, achieving first place in five out of eight metrics in AudioMOS Challenge 2025 Track3.
9 UpdatedSep 15, 2025 -
torchstat2 Public
Forked from Phoenix8215/torchstat2Model analyzer in PyTorch
Python UpdatedAug 31, 2025 -
unmute Public
Forked from kyutai-labs/unmuteMake text LLMs listen and speak
Python MIT License UpdatedAug 26, 2025 -
DeSTA2.5-Audio Public
Forked from kehanlu/DeSTA2.5-AudioThe official repo of DeSTA2.5-Audio
Python UpdatedJul 23, 2025 -
floss-torch Public
Forked from yukara-ikemiya/floss-torchPyTorch implementation of "Source Separation by Flow Matching (FLOSS)" by Google DeepMind
Python MIT License UpdatedJul 21, 2025 -
Swift-Net Public
Forked from JusperLee/Swift-NetPower-Guided Grouped SRU for Real-Time Causal Audio-Visual Speech Separation
Python Other UpdatedJul 11, 2025 -
TIGER Public
Forked from JusperLee/TIGERTIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation
Python UpdatedApr 8, 2025 -
RAMP_MOS Public
Forked from NKU-HLT/RAMP_MOSRetrieval-Augmented MOS Prediction with Prior Knowledge Integration
Python UpdatedMar 23, 2025 -
IIANet Public
Forked from JusperLee/IIANetThis is the demo of our paper "IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation".
Python Apache License 2.0 UpdatedMar 12, 2025 -
LLaSE-G1 Public
Forked from Kevin-naticl/LLaSE-G1LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement
Python UpdatedMar 9, 2025 -
PyTorch-Tutorial-2nd Public
Forked from TingsongYu/PyTorch-Tutorial-2nd《Pytorch实用教程》（第二版）无论是零基础入门，还是CV、NLP、LLM项目应用，或是进阶工程化部署落地，在这里都有。相信在本书的帮助下，读者将能够轻松掌握 PyTorch 的使用，成为一名优秀的深度学习工程师。
Jupyter Notebook UpdatedJan 27, 2025 -
dynamic-superb Public
Forked from dynamic-superb/dynamic-superbThe official repository of Dynamic-SUPERB.
Python UpdatedJul 22, 2024 -
pytorch-OpCounter Public
Forked from Lyken17/pytorch-OpCounterCount the MACs / FLOPs of your PyTorch model.
Python MIT License UpdatedJul 8, 2024 -
-
-
-
timit Public
Forked from philipperemy/timitThe DARPA TIMIT Acoustic-Phonetic Continuous Speech Corpus.
UpdatedMar 5, 2022
{{ message }}