Tiffany-Huang
Follow
Stars
PyTorch implementation of " Synthesizing Audio with Generative Adversarial Networks"
Fully reproduce the paper of StarGAN-VC. Stable training and Better audio quality .
Experimenting with simple GAN architectures for music & audio using pytorch
WaveGAN: Learn to synthesize raw audio with generative adversarial networks
Introducing multi-channel U-Net for Music Source Separation trained using weighted multi-task loss.
Implementation of the Wave-U-Net for audio source separation
pytorch version of the unet model for audio super resolution
The Matlab Simulation codes for Hybrid Beamforming for Millimeter Wave Systems Using the MMSE Criterion.
Beamforming design with deep learning.
⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.
proof of concept for a transformer-based time series prediction model
A live speech recognition using Facebooks wav2vec 2.0 model.
DNN assisted Kalman filter for time domain speech enhancement
Universal Deep neural network based speech enhancement demo and tools, well pre-trained DNN model
Voice activity detection (VAD) toolkit including DNN, bDNN, LSTM and ACAM based VAD. We also provide our directly recorded dataset.
A tutorial for Speech Enhancement researchers and practitioners. The purpose of this repo is to organize the world’s resources for speech enhancement and make them universally accessible and useful.
GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型
Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together
High-speed download of LLaMA, Facebook's 65B parameter GPT model
Convertion program from Matlab to C++ using Armadillo