ivanvovk/compressed-tacotron2-pytorch

Compressed version of Tacotron 2 using Tensor Train + Waveglow.

39
/ 100
Emerging

This project helps reduce the computational resources needed for text-to-speech (TTS) systems. It takes an existing Tacotron 2 and WaveGlow model and compresses it, yielding a smaller model that generates speech faster. This would be used by engineers or researchers working on deploying efficient voice synthesis applications.

No commits in the last 6 months.

Use this if you need to deploy a text-to-speech system that synthesizes audio quickly and uses less memory, particularly for real-time applications or environments with limited resources.

Not ideal if you are looking for an out-of-the-box, pre-trained, highly accurate text-to-speech model without needing to worry about model compression or fine-tuning.

voice-synthesis speech-technology model-optimization real-time-audio natural-language-processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

22

Forks

9

Language

Jupyter Notebook

License

MIT

Last pushed

Dec 26, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ivanvovk/compressed-tacotron2-pytorch"

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