CSTR-Edinburgh/merlin

This is now the official location of the Merlin project.

51
/ 100
Established

Merlin helps speech technology researchers create custom synthetic voices. It takes linguistic features from text (processed by a front-end) and outputs the acoustic parameters needed for a vocoder to generate natural-sounding speech. This system is ideal for academic researchers and advanced practitioners in speech synthesis looking to build state-of-the-art voice models.

1,321 stars. No commits in the last 6 months.

Use this if you are a speech technology researcher or engineer and need to build highly customized, neural network-based statistical parametric speech synthesis systems.

Not ideal if you need a simple, out-of-the-box text-to-speech solution or do not have expertise in speech synthesis and neural networks.

speech-synthesis text-to-speech voice-generation acoustic-modeling deep-learning-for-speech
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,321

Forks

431

Language

Python

License

Apache-2.0

Last pushed

Mar 03, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/CSTR-Edinburgh/merlin"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.