I am looking for a machine learning engineer with extensive knowledge in ASR decoder such as CTC recognition algorithm C++, and python. We have a C++ decoder library/module that we would like to modify. The task itself is not hard, but you must be familiar with machine learning algorithm and C++.
This is the link to the decoder.
[login to view URL]
the decoder is written in C++ and the entire project is under folder /swig.
[login to view URL] is the code we use to compile the decoder to python modules.
[login to view URL] is the python interface that we use to call the decoder. All the functions are calling the swig_decoder module.
The current decoder returns the whole transcript. We instead, we need to extract word level confidence and word level timestamps. If you read the above contents, when you apply for this project, please address your favorite tea.
modify the decoder code package to support word level time stamp and word level confidence.
modify the swig_wrapper to support interface to return word level time stamp and word level confidence as a class
11 freelancers are bidding on average $155 for this job
hello, i am red hat certified engineer and i really want to work on your project i read the task carefully thanks.................................................
Hi,how are you All will be enough for me. I am Python Expert and it's nothing for me I can be helpful for you and your project. High performance, bug-free, all-time communication are all promised. Thanks
Hi, Dear I have much experience in automatic speech recognition. Last month I finished a job on word level timing in DeepSpeech and Kaldi. You may check at my profile. I believe I can help you. Sincerely Kornienko.