An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
-
Updated
Sep 29, 2026 - Python
#
bigvgan
Here are 7 public repositories matching this topic...
A single-file implementation of BigVGAN generator
pytorch speech-synthesis audio-synthesis music-synthesis neural-vocoder singing-voice-synthesis audio-generation bigvgan
-
Updated
Sep 8, 2024 - Python
PitchFlowNet: An Empirical Study of Architectural Integration in Single-Stage Text-to-Speech (SOICT 2026). Code, configs, training records and evaluation of a VITS/Piper-based TTS with BigVGAN, VITS2 and F0 components.
text-to-speech pytorch tts speech-synthesis pitch piper ljspeech ablation-study vits vits2 piper-tts bigvgan
-
Updated
Oct 28, 2026 - Python
Four-stage audio pipeline: split a track into content and style, calibrate a 160-D genre space, and remaster it into a target genre.
audio python music generative-audio pytorch style-transfer spectrogram diffusion-models encodec bigvgan
-
Updated
Sep 30, 2026 - Python
Pure C99 inference engine for FastH3 (35B MiniMax-H3): text-to-video + audio diffusion on 16GB laptops via NVMe cyclic ring streaming and offline AdaLN folding.
c deep-learning c99 openmp avx2 minimax dit multimodal video-generation interface-engine zero-dependencies diffusion-models cpu-inference generative-ai gguf text-to-video-generation bigvgan ondevice-ai weight-streaming fasth3
-
Updated
Nov 11, 2026 - C
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
-
Updated
Jan 17, 2026 - Python
Add this topic to your repo
To associate your repository with the bigvgan topic, visit your repo's landing page and select "manage topics."