stevenhillis Goto Github PK
Name: Steven Hillis
Type: User
Company: Deepgram
Bio: Research Scientist. Speech, NLP, & ML.
Twitter: steven_hillis
Location: Milwaukee
Blog: stevenhillis.com
Name: Steven Hillis
Type: User
Company: Deepgram
Bio: Research Scientist. Speech, NLP, & ML.
Twitter: steven_hillis
Location: Milwaukee
Blog: stevenhillis.com
Data manipulation and transformation for audio signal processing, powered by PyTorch
A curated list of awesome papers on contextualizing E2E ASR outputs
Automated budgeting template using google sheets
Array-based CKY Parser for English with Coarse-to-Fine Parsing
C Minimal Perfect Hashing Library
Numpy implementation of a cnn module
Decision Tree for Binary Classification
Generative LSTM Language Model
Numpy implementation of a GRU Cell
Implement the Listen-Attend-Spell with Improvements
Learn to solve a simple maze with reinforcement learning
MNIST task using simple MLP
Code for multimodal/multilingual G2P system
Character-level model with (pyramidal) encoder-decoder and attention for IWSLT 2014 DE -> EN dataset, reaching 28.38 BLEU.
Numpy implementation of an multilayer perceptron
Use a Primal SVM (with Perceptron for Feature Extraction) to rerank a parser
Label aligned speech data with phoneme state using a multilayer perceptron
Recognize phonemes from unaligned speech data using LSTM and CTC Decoding
Use Hidden Markov Model to tag parts of speech
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
This library provides common speech features for ASR including MFCCs and filterbank energies.
Use logistic regression to analyze the sentiment of movie reivews
Train a ShuffleNetV2 as a facial classifier, and then transfer the trained model for use on a facial verification task.
Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch
Python package to accelerate the sparse matrix multiplication and top-n similarity selection
Blog with Jekyll and github pages.
Perform Sentiment Classification using a CNN model.
Reimplementing the Tranx system (Yin and Neubig 2018)
Trigram language model with kneser-ney smoothing
Implementation of Voicebox, new SOTA Text-to-speech network from MetaAI, in Pytorch
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.