Haohe Liu / 刘濠赫

AudioLDM. AudioLDM: Generate speech, sound effects, music and beyond, with text.

AudioLDM2. Text-to-Audio/Music Generation

versatile_audio_super_resolution. Versatile audio super resolution (any -> 48kHz) with AudioSR.

voicefixer. General Speech Restoration

audioldm_eval. This toolbox aims to unify audio generation model evaluation for easier comparison.

AudioLDM-training-finetuning. AudioLDM training, finetuning, evaluation and inference.

voicefixer_main. General Speech Restoration

SemantiCodec-inference. Ultra-low bitrate neural audio codec (0.31~1.40 kbps) with a better semantic in the latent space.

ssr_eval. Evaluation and Benchmarking of Speech Super-resolution Methods

2021-ISMIR-MSS-Challenge-CWS-PResUNet. Music Source Separation; Train & Eval & Inference piplines and pretrained models we used for 2021 ISMIR MDX Challenge.

Subband-Music-Separation. Pytorch: Channel-wise subband (CWS) input for better voice and accompaniment separation

torchsubband. Pytorch implementation of subband decomposition

SemantiCodec. HTML

diffres-python. Learning differentiable temporal resolution on time-series data.

DCASE_2022_Task_5. System that ranks 2nd in DCASE 2022 Challenge Task 5: Few-shot Bioacoustic Event Detection

courseProject_Compiler. java implementation of NWPU Compiler course project-西工大编译原理-试点班

ontology-aware-audio-tagging. Python

kmeans_pytorch. kmeans using PyTorch

Key-word-spotting-DNN-GRU-DSCNN. key word spotting GRU/DNN/DSCNN

CLAP. Learning audio concepts from natural language supervision

DM_courseProject. KNN Bayes 西北工业大学 NWPU 数据挖掘与分析

youtube-8m-videos-downloader. Download videos from YouTube-8M dataset for testing

AudioSetCaps. AudioSetCaps: An Enriched Audio-Caption Dataset using Automated Generation Pipeline with Large Audio and Language Models

audio-ai-timeline. A timeline of the latest AI models for audio generation, starting in 2023!

netease_downloader. 网易云音乐上以歌单为单位进行下载

conditional-flow-matching. TorchCFM: a Conditional Flow Matching library

SongEval. A song aesthetic evaluation toolkit trained on SongEval.

SatProj. 西北工业大学应用综合实验

hifi-gan. HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

all-in-one. All-In-One Music Structure Analyzer

vector-quantize-pytorch. Vector (and Scalar) Quantization, in Pytorch

Open-Sora. Open-Sora: Democratizing Efficient Video Production for All

Speech-Emotion-Classification-with-PyTorch. This repository contains PyTorch implementation of 4 different models for classification of emotions of the speech.

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

audiotools. Object-oriented handling of audio data, with GPU-powered augmentations, and more.

Channel-wise-Subband-Input. The demos of paper: Channel-wise Subband Input for Better Voice and Accompaniment Separation on High Resolution Music

resemble-enhance. AI powered speech denoising and enhancement

YuE. YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

EfficientAT. This repository aims at providing efficient CNNs for Audio Tagging. We provide AudioSet pre-trained models ready for downstream training and extraction of audio embeddings.

deep-clustering. deep clustering method for single-channel speech separation

fid-metrics. A toolkit for computing Fréchet Inception Distance (FID) & Fréchet Video Distance (FVD) metrics.

MuQ. Official repository of the paper "MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization".

DiffRhythm. Di♪♪Rhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion

mushra_test_2024_April.

video_features. Extract video features from raw videos using multiple GPUs. We support RAFT and PWC flow frames as well as S3D, I3D, R(2+1)D, VGGish, CLIP, ResNet features.

colab_collection. Jupyter Notebook

audio-dataset. Audio Dataset for training CLAP and other models

psds_eval. Polyphonic Sound Detection Score (PSDS)

visa-monitor. 实时监控可预约签证的时间，有更早的就邮件通知