-
๐ Hi, Iโm @cvillela
-
Making art at Refik Anadol Studio
-
My research focus lies on Deep Learning, Audio Processing, Natural Language Processing and Machine Learning Engineering
-
Currently I'm actively working on:
- Building scalable interfaces for model interaction and data analysis for large and unstructured datasets
- Deep audio embedding extraction and manipulation for real-time streaming reccomendation systems
- Scalable audio processing pipelines for noise reduction, silence removal and audio effects.
- Generative Audio-to-Audio, Text-to-Audio and LLMs.
- Graph Search, Knowledge Graphs and Path Planning algorithms for latent space navigation.
cvillela / audio_extractor Goto Github PK
View Code? Open in Web Editor NEWRepo configured with useful functions for preprocessing, segmenting and creating audio datasets, as well as extracting embeddings
License: MIT License