Skip to main content

Blog Portal Docs

Posts

How to build smarter turn detection for Voice AI
How to Finetune Sesame AI's Speech Model on New Languages and Voices
Exploring the trade-off between speed and accuracy in real-time transcription
Sparse All-Reduce in PyTorch
The.Shed: Using Speechmatics Capabilities in real-time
An Almost Pointless Exercise in GPU Optimization
Reduce Model Tuning Costs with MuP
Building a Radio Translation Streaming Service in Python
Improving Speaker Diarization with Self-supervised Learning
How to Access Microphones Through the Browser API
How to Deploy HuggingFace Translation Models on GPU Servers
Fast and Accurate GPU Quantization for Transformers
How to Accurately Time CUDA Kernels in Pytorch

Tags

A

asr1

B

back end1

C

C++1
capabilities1
CUDA3

D

diarization1

F

front end1

G

GPU1

H

hello1
huggingface1

J

javascript1

M

memory bandwidth1
monitoring1

N

NCCL1
nextjs1
NSight Compute1

P

profiling1
python1
pytorch3
PyTorch1

Q

quantization1

R

real-time1

S

shared memory1
ssl1

T

test1
the-shed1
thread divergence1
transformers1
translation1
triton-server1
tts1
turn-detection1
typescript1

V

voice-ai1

W

websockets1

Product

Features and Deployments
How We Compare
Case Studies

Use Cases

Contact Center Solutions
Media & Event Captioning
Video Distribution Platforms
Media Monitoring
Meeting Platforms

Pricing

Pricing Options

Resources

Blog and Latest News
Gartner Reports
Whitepapers and Reports
Events
Service Status

About

About Us
Careers
Contact Us

Privacy Policy
Terms of Website
Terms of Service
Cookie Policy

Copyright © Speechmatics 2023