Yifan Zhang's Projects
Ansible role for scrapyd.
apihub web interface
FastCGI support for Kaldi ASR
An experimental open-source attempt to make GPT-4 fully autonomous.
replicate c4 dateset process without Apache Beam, use Slurm instead
Fetch CCTV news video and corresponding text
Cloud-based Automatic Speech Recognition (ASR) platform and a public ASR webservice.
Cookiecutter template for tanbih worker
generic helper functions in c++
TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...
Deep neural networks for voice conversion (voice style transfer) in Tensorflow
Implementation of "Teaching Machines to Read and Comprehend" proposed by Google DeepMind
A small Javascript library for browser-based real-time speech recognition, which uses Recorderjs for audio capture, and a WebSocket connection to the Kaldi GStreamer server for speech recognition.
my dotrc repository
Methods to allow using HTML code with CoreText
Standard toolset classes and categories
Text Alignment with openFst
tools for streaming, linting, and parsing GDELT data
lightweight, standalone C++ inference engine for Google's Gemma models.
gentle forced aligner
GStreamer plugin around Kaldi's online neural network decoder
An operating system operates on data (JSON). Data is decoupled from how it is used, how it is displayed.
chef cookbook for KALDI
Real-time full-duplex speech recognition server, based on the Kaldi toolkit and the GStreamer framwork.
Proof of concept for running Kaldi ASR decoder on iOS
C++ library for Api.ai