Running LSTM neural networks on an Imagination NNA
January 8, 2021
Speech recognition has become more relevant in recent years: it enables computers to translate spoken language into text. It can be found in different types of applications, such as translators or closed captioning. An example of this technology is Mozilla’s DeepSpeech, an open-source speech-to-text engine, which uses a model trained by machine learning techniques based on Baidu’s Deep Speech research paper. We are going to provide an overview of how we are running version 0.5.1 of this model, by accelerating a static LSTM network on the Imagination neural network accelerator (NNA), with the goal of creating a prototype of a voice assistant for an automotive use case.
To read the full article, click here
Related Blogs
- ChiPy®: Bridge Neural Networks and C++ on Silicon — Full Inference Pipelines with Zero CPU Round-Trips
- FPGAs take on convolutional neural networks
- Why the PowerVR 2NX NNA is the future of neural net acceleration
- Self-Compressing Neural Networks
Latest Blogs
- Satellite communications are no longer as secure as assumed
- Why Hardware Monitoring Needs Infrastructure, Not Just Sensors
- Why Post-Quantum Cryptography Doesn’t Replace Classical Cryptography
- The Silent Guardian of AI Compute - PUFrt Unifies Hardware Security and Memory Repair to Build the Trust Foundation for AI Factories
- Heterogeneous NPU Data Movement Tax: Intel's Own Slides Tell the Story