Stars
audio-processing-module is extracted from WebRTC.
to illustrate how to removal a Neural Network from pc to FPGA board ,it contain all the code include c code worked in pc,HLS prj accelerate code in FPGA,and implacement in block design and with SDK…
For self-experimental study only,this is a project clone from whiteeate.
PyTorch implementation of "Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss" (ICASSP 2020)
A streamable speech recognition model with transformer encoders and RNN-T loss
I will build Transformer from scratch
A python realization of the paper Learning Deep Representations of Fine-Grained Visual Descriptions
Python Implementation for HybridCNN
MXNet OCR implementation. Including text recognition and detection.
A collection of MATLAB routines for acoustical array processing on spherical harmonic signals, commonly captured with a spherical microphone array.
Production First and Production Ready End-to-End Speech Recognition Toolkit
Reading and writing Windows WAVE file format.
RV1126 OHD Firmware (work in progress) based on rockchip rv1126 v2.2.0 sdk (released 25.08.2021
Transformer: PyTorch Implementation of "Attention Is All You Need"
A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.
A higher-level Neural Network library for microcontrollers.