Build a custom vocabulary to enhance speech-to-text transcription accuracy with Amazon Transcribe

Favorite Amazon Transcribe is a fully-managed automatic speech recognition (ASR) service that makes it easy for developers to add speech-to-text capabilities to applications. Depending on your use case, you may have domain-specific terminology that doesn’t transcribe properly (e.g. “EBITDA” or “myocardial infarction”). In this post, we will show you how

Read More
Shared by AWS Machine Learning July 3, 2019

Deploying PyTorch inference with MXNet Model Server

Favorite Training and inference are crucial components of a machine learning (ML) development cycle. During the training phase, you teach a model to address a specific problem. Through this process, you obtain binary model files ready for use in production. For inference, you can choose among several framework-specific solutions for

Read More
Shared by AWS Machine Learning July 2, 2019

Winning by eliminating mistakes

Favorite In some settings, winning by eliminating mistakes is the best strategy Image from wikimedia commons Wimbledon fortnight has started in the UK – the two weeks of the year when the TV schedules are taken over by professional tennis. This reminded me of a post from the excellent Farnham Street

Read More
Shared by Nick Milton July 2, 2019

Support for Apache MXNet 1.4 and Model Server in Amazon SageMaker

Favorite Apache MXNet is an open-source deep learning software framework used to train and deploy deep neural networks. Data scientists and machine learning (ML) developers love MXNet due to its flexibility and efficiency when building deep learning models. Amazon SageMaker is committed to improving the customer experience for all ML frameworks and libraries, including

Read More
Shared by AWS Machine Learning July 1, 2019

How KM is migrating from Big Companies to SMEs

Favorite So far, Knowledge Management has largely been a Big Company game, but this is changing. This is another conclusion from the Knoco Knowledge Management survey, and is neatly illustrated in the bar chart shown here. The survey was conducted in 2 waves – 204 and 2017, and received submissions

Read More
Shared by Nick Milton July 1, 2019

Bigger communities of practice are more effective, data shows

Favorite The bigger a community of practice is, the more value it delivers. At least according to our KM surveys.  Knoco conducted two major surveys of knowledge management programs in 2014 and 2017, collecting in total more than 700 results. As part of the survey, participants were asked whether Communities

Read More
Shared by Nick Milton June 28, 2019