Kyubyong/dc_tts

A TensorFlow Implementation of DC-TTS: yet another text-to-speech model

51
/ 100
Established

Implements the DC-TTS architecture with a two-stage pipeline: Text2Mel generates mel-spectrograms from text using guided attention for monotonic alignment, while SSRN (speaker-dependent vocoder) converts spectrograms to waveforms. Supports multilingual training across English and Korean datasets, with practical modifications including layer normalization and learning rate decay to improve convergence over the original paper's approach.

1,159 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,159

Forks

360

Language

Python

License

Apache-2.0

Last pushed

Apr 14, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Kyubyong/dc_tts"

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