Pinned Repositories
audio
Data manipulation and transformation for audio signal processing, powered by PyTorch
awesome-asr-contextualization
A curated list of awesome papers on contextualizing E2E ASR outputs
budget
Automated budgeting template using google sheets
CKY_Parser_with_Coarse_to_Fine
Array-based CKY Parser for English with Coarse-to-Fine Parsing
cmph
C Minimal Perfect Hashing Library
GRU_By_Hand
Numpy implementation of a GRU Cell
LAS
Implement the Listen-Attend-Spell with Improvements
Parsing_Reranker_with_SVM
Use a Primal SVM (with Perceptron for Feature Extraction) to rerank a parser
Phoneme_Recognition
Recognize phonemes from unaligned speech data using LSTM and CTC Decoding
ShuffleNetV2_Facial_Verification
Train a ShuffleNetV2 as a facial classifier, and then transfer the trained model for use on a facial verification task.
stevenhillis's Repositories
stevenhillis/awesome-asr-contextualization
A curated list of awesome papers on contextualizing E2E ASR outputs
stevenhillis/Phoneme_Recognition
Recognize phonemes from unaligned speech data using LSTM and CTC Decoding
stevenhillis/ShuffleNetV2_Facial_Verification
Train a ShuffleNetV2 as a facial classifier, and then transfer the trained model for use on a facial verification task.
stevenhillis/GRU_By_Hand
Numpy implementation of a GRU Cell
stevenhillis/LAS
Implement the Listen-Attend-Spell with Improvements
stevenhillis/Parsing_Reranker_with_SVM
Use a Primal SVM (with Perceptron for Feature Extraction) to rerank a parser
stevenhillis/audio
Data manipulation and transformation for audio signal processing, powered by PyTorch
stevenhillis/budget
Automated budgeting template using google sheets
stevenhillis/CKY_Parser_with_Coarse_to_Fine
Array-based CKY Parser for English with Coarse-to-Fine Parsing
stevenhillis/CNN_By_Hand
Numpy implementation of a cnn module
stevenhillis/Decision_Tree_Binary_Classifier
Decision Tree for Binary Classification
stevenhillis/Generative_LM
Generative LSTM Language Model
stevenhillis/Maze_Solver_With_Q_Learning
Learn to solve a simple maze with reinforcement learning
stevenhillis/MNIST_Classification_With_MLP
MNIST task using simple MLP
stevenhillis/Multimodal-Multilingual-G2P
Code for multimodal/multilingual G2P system
stevenhillis/neural-mt-de-en
Character-level model with (pyramidal) encoder-decoder and attention for IWSLT 2014 DE -> EN dataset, reaching 28.38 BLEU.
stevenhillis/NN_By_Hand
Numpy implementation of an multilayer perceptron
stevenhillis/Phoneme_Labeling_With_MLP
Label aligned speech data with phoneme state using a multilayer perceptron
stevenhillis/POS_Tagging_With_HMM
Use Hidden Markov Model to tag parts of speech
stevenhillis/pyannote-audio
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
stevenhillis/python_speech_features
This library provides common speech features for ASR including MFCCs and filterbank energies.
stevenhillis/Sentiment_Analysis_with_Logistic_Regression
Use logistic regression to analyze the sentiment of movie reivews
stevenhillis/soundstorm-pytorch
Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch
stevenhillis/sparse_dot_topn
Python package to accelerate the sparse matrix multiplication and top-n similarity selection
stevenhillis/stevenhillis.github.io
Blog with Jekyll and github pages.
stevenhillis/Text-Classification
Perform Sentiment Classification using a CNN model.
stevenhillis/TranxConalaBaseline
Reimplementing the Tranx system (Yin and Neubig 2018)
stevenhillis/Trigram_LM_with_KN_Smoothing
Trigram language model with kneser-ney smoothing
stevenhillis/voicebox-pytorch
Implementation of Voicebox, new SOTA Text-to-speech network from MetaAI, in Pytorch
stevenhillis/Word_Alignment
Use three methods to build a word aligner: a heuristic, IBM Model 1, and a Position-Sensitive HMM Aligner