Pinned Repositories
trainable-STFT-Mel
Understanding Audio Features via Trainable Basis Functions
nnAudio_tutorial
This is the tutorial for nnAudio :)
nnAudio-vs-librosa
heungky's Repositories
heungky/amazon-kendra-langchain-extensions
heungky/tutorials-LangChain
heungky/notebooks
Notebooks using the Hugging Face libraries 🤗
heungky/ai_chatgpt_experiments
heungky/SDSC-Spark
Hands-On Workshops on Apache Spark
heungky/speach_to_text_nlp_analysis
This repository is to test a pipeline to analyse a recorded interview with AWS Transcribe and AWS Comprehend Services
heungky/numpy-100
100 numpy exercises (with solutions)
heungky/AudioLoader
PyTorch Dataset for Speech and Music audio
heungky/slakh_loader
A PyTorch Dataset for Slakh2100
heungky/MERP
Dataset and benchmark models for emotion prediction of music with profile info
heungky/demucs_lightning
PyTorch lightning version of demucs
heungky/nnAudio_tutorial
This is the tutorial for nnAudio :)
heungky/nnAudio-vs-librosa
heungky/DALLE-pytorch
Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
heungky/tr
Free Offline OCR 离线的中文文本检测+识别SDK. Text detection
heungky/trainable-STFT-Mel
Understanding Audio Features via Trainable Basis Functions
heungky/demucs
Code for the paper Hybrid Spectrogram and Waveform Source Separation
heungky/pytorch_template
Template that combines PyTorch Lightning and Hydra
heungky/Kelly_Coin_flips
heungky/AMAAI-guidebook
heungky/Fastaudio
FastAudio is a Learnable Audio Frontend team Magnum's designed for the ASVspoof 2021 challenge