Riva Speech Recognition
Riva Speech Recognition
Release Version: 1.3.0
Release Date: May 6, 2024
Description
By using Riva Speech Recognition (SR) plugin to UniMRCP Server, IVR platforms can utilize NVIDIA Riva Speech-to-Text API via the industry-standard Media Resource Control Protocol (MRCP) version 1 and 2.
NVIDIA Riva Speech-to-Text API performs speech to text conversion powered by machine learning providing the following main features.
Streaming Speech Recognition
Supports efficient streaming speech transcription.
Low Latency
Intermediate transcripts are returned with low latency.
Efficient Feature Extraction
GPU-accelerated feature extraction.
Multiple Acoustic Models
Multiple (and growing) acoustic model architecture options accelerated by NVIDIA TensorRT
Beam Search Decoder
Beam search decoder based on n-gram language models
Voice Activity Detection
CTC-based voice activity detection algorithms.
Automatic Punctuation
Automatic punctuation can optionally be enabled.
Alternate Transcripts
Ability to return top-N transcripts from beam decoder
Word-level Timestamps
Word-level timestamps can optionally be returned.
Inverse Text Normalization
Inverse text normalization (ITN) is supported.
Addon Packages
Complimentary Products
Alternate Products
Solutions
IVR
platform
MRCP
server
- Riva Speech Recognition
Solutions
IVR
platform
MRCP
server
- Riva Speech Recognition
Documentation
This section provides references to installation, configuration and usage guides.
Installation
RPM Installation Manual
WIKIObtain and install the RPM packages for Red Hat / CentOS.
Deb Installation Manual
WIKIObtain and install the deb packages for Debian / Ubuntu.
Usage
Usage Manual
WIKILearn how to configure and use the plugin.
Supplimentary
Release Notes
WIKITrack down the changes introduced in each release.
Licensing
