sushanthiray

I've been working on the problem of speaker diarization in the wild for better part of this year. Would love to have a chat with you to see if our diarization utility can help you guys out. Here is the link: https://www.deepaffects.com/apis

My email is in my profile.

DeepAffects | Mumbai, India | Machine Learning Engineers, Data Engineers | Full-time | Onsite

DeepAffects (https://www.deepaffects.com) is a next-generation Enterprise Speech Analytics Company. We solve problems in speech domain using advanced Deep learning and Machine Learning techniques. Few examples of the problems are -

* Speaker Diarization on mono-channel recordings in noisy environment.

* Low latency Speech Enhancement.

* Audio Redaction for PII data. Think GDPR compliance directly on audio.

Technologies Used: Tensorflow, Keras, Kubernetes, Docker, Pub Sub Queues, Cassandra, Python

If this sounds exciting to you, send an email to sushant DOT hiray _at_ seernet DOT io with the subject as HN

DeepAffects | Mumbai, India | Machine Learning Engineers, Data Engineers | Full-time, Interns | Onsite

At DeepAffects (https://www.deepaffects.com) we're building next generation Speech Analytics for Enterprises. We're working on interesting research problems and putting them into production. Some of the problems that we've worked on in the past:

1. Limited Resource Speaker Diarization 2. Minimum Latency Speech Enhancement 3. Audio redaction to remove personally identifiable information. Think GDPR compliance directly on speech.

We're serving various enterprises across the globe and are hiring ML Engineers and Data Engineers to help us scale and solve many such interesting problems.

Technologies: Tensorflow, Keras, Kubernetes, Docker, Python, Go, Cassandra

If this sounds interesting to you, let us chat. Please send an email with subject: HN to sushant DOT hiray a_t seernet DOT io

Take a look at the Coursera specialization: Mathematics for Machine Learning [1]. The specialization isn't free but you can certainly apply for financial aid.

[1]: https://www.coursera.org/specializations/mathematics-machine...

I'm currently using Google Cloud Storage for storing and archiving data. Using regional storage has helped us while running production jobs which ingest this data. Once the data is processed, we move to coldline storage for archiving.

*Hacker Noon

> I think you do this better with filter-branch too. But I don't know that command as much.

It goes like this:

   git filter-branch --env-filter \
       'if [ $GIT_COMMIT=186ba2fd6bca97c901194d9450c694c2836064d2 ]
         then
            export GIT_AUTHOR_DATE="Fri Apr 11 21:38:53 2014 -0800"
            export GIT_COMMITTER_DATE="Sat Apr 12 01:01:01 2014 -0700"
        fi'