shoegazerstella's repositories
instruments_activity_detection
Detect individual instruments activity in an audio file. π€πΉπΈπ₯
midi2img2vae
a VAE trained on the image representation of midi files. πΎ
tacotron2_cpu
NVIDIA Tacotron2 to run on cpu
DeepSpeech_CPU_py37
A CPU version of DeepSpeech for python 3.7 π£οΈπ
siameseTextSimilarityBERT
Siamese text similarity network using BERT embeddings
shoegazerstella.github.io
my personal website
musicnnCondVAE
ποΈ Sound generation using VAE, conditioned on musicnn tags π·οΈ
AutoPST
Global Rhythm Style Transfer Without Text Transcriptions
cryptopunkgenerator
Generate CryptoPunk-style avatars
Deep-Learning-with-CryptoPunks
Some Exploratory Deep Learning tasks on the multi-billion dollar CryptoPunk NFT collection.
elasticsearchquerygenerator
Create Complex Elastic Search Query in Seconds Please see documentation for more details
FastSpeech2
An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"
GPT-2-AgainstHumanity
Use GPT-2 to generate new cards for the popular game Cards Against Humanity
hf-experiments
Experiments with Hugging Face π€
lstm-siamese-text-similarity
βοΈ It is keras based implementation of siamese architecture using lstm encoders to compute text similarity
OpenNE
An Open-Source Package for Network Embedding (NE)
Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
spotify-readme
Dynamic realtime profile ReadMe linked with spotify