Josh Meyer

easy-kaldi. Use your data to create a speech recognition system in Kaldi. Fast.

markdown-datasheet-for-datasets. Markdown template for Dataseets for Datasets

multi-task-kaldi. An example directory for running Multi-Task Learning training on Kaldi neural networks. In Kaldi-speak, this is an egs dir for nnet3 training.

tensorflow-tutorial. Code for email classification in TensorFlow.

common-voice-forced-alignments. Forced Alignments for Common Voice

jphones. A Python3 program for converting Japanese words and numbers into phonemes.

speakerID-challenge. A recipe for creating a Speaker Identification system built on Kaldi.

common-voice-stats. A living document for all things Common Voice.

kaldi-tf. Scripts for exporting Kaldi labeled data into TensorFlow

nnet2-simple. A set of scripts for running the bare bones of Kaldi's nnet2.

jrmeyer.github.io. A site for things

awesome-audio-foundation-models.

cv. Joshua's CV in LaTeX

web-corpus. Tool for scraping text from websites

arxiv-sanity-lite. arxiv-sanity lite: tag arxiv papers of interest get recommendations of similar papers in a nice UI using SVMs over tfidf feature vectors based on paper abstracts.

TTS. Deep learning for Text to Speech

alphabets. Cycript

ftyers.github.io. HTML

vowel-synthesizer. MATLAB

interspeech-2018. I submitted this paper to Interspeech 2018. The paper was not accepted. The reviewer comments are included in the repo.

defense. Gnuplot

manas. Python

basic-latex-template. A super simple LaTeX template for little everyday things

flatten-git-repo. Turn a git repo into a flat dir of files while preserving structure. Useful to feed into LLM context window

xtts-streaming-server. Python

ljspeech-text. Text from the LJSpeech Corpus

conferences. list of conferences for ASR research

mlslp. My submission to the 2018 Machine Learning in Speech and Language Processing Workshop

open-funding. A guide for researching ways of funding open source projects.

twitter. Python

librivox.

covid-kws.

machine_learning. Some small scripts for playing with and vizualizing neural nets and Gaussians.