k2-fsa/k2

FSA/FST algorithms, differentiable, with PyTorch compatibility.

CudaC++PythonCMakeCShell
This is stars and forks stats for /k2-fsa/k2 repository. As of 23 Apr, 2024 this repository has 952 stars and 234 forks.

k2 The vision of k2 is to be able to seamlessly integrate Finite State Automaton (FSA) and Finite State Transducer (FST) algorithms into autograd-based machine learning toolkits like PyTorch and TensorFlow. For speech recognition applications, this should make it easy to interpolate and combine various training objectives such as cross-entropy, CTC and MMI and to jointly optimize a speech recognition system with multiple decoding passes including lattice rescoring and confidence estimation. We...
Read on GithubGithub Stats Page
repotechsstarsweeklyforksweekly
onplus/v2heroDockerfileShellGo47701.2k0
gitithan/zzcfg.dEmacs LispCommon LispJava0000
relaypro-open/imetricsErlangPython15010
ddosify/ddosifyGoShellDockerfile7.8k03580
ministryofjustice/cloud-platform-environmentsHCLRubyGo600320
minexew/ShrineHolyCC++C1.4k+275+1
aenarete/KiteSimulators.jlJuliaBatchfileShell11010
EssayKillerBrain/EssayTopicPredictJupyter NotebookPythonShell490-1820
aws-samples/aws-machine-learning-university-accelerated-nlpJupyter NotebookPython2.2k05650
Paisseon/SatellaJailedSwiftShellMakefile6310670