NVIDIA/waveglow
waveglow
A Flow-based Generative Network for Speech Synthesis
Builder
NVIDIA
NVIDIA • big-tech
Stars
2,338
Using upstream star count
Forks
537
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
Nov 8, 2018
Project creation date
README Summary
WaveGlow is a flow-based generative network for speech synthesis developed by NVIDIA that can generate high quality speech from mel-spectrograms. It combines insights from Glow and WaveNet to produce audio that sounds natural and trains efficiently. The model uses invertible 1x1 convolutions and affine coupling layers to directly generate audio waveforms.
AI Dev Skills
Unmapped
Flow-based Generative ModelsSpeech SynthesisNormalizing FlowsMel-spectrogram ProcessingAudio Signal ProcessingGenerative Neural NetworksWaveNet ArchitectureVocoder Implementation
Tags
Flow-based Generative ModelsSpeech SynthesisNormalizing FlowsMel-spectrogram ProcessingAudio Signal ProcessingGenerative Neural NetworksWaveNet ArchitectureVocoder ImplementationAudio Content CreationFlow-based ModelsSelf-hostedVoice GenerationMedia ProductionCloud APIGamingOn-premiseAudioAudiobook ProductionGenerative AIEntertainmentText-to-Speech SynthesisSpeech EnhancementAssistive TechnologyVoice CloningPython
Taxonomy
AI Trends
Deployment Context
Modalities
Skill Areas
Recent Activity
Updated 2 years ago
7 Days
0
30 Days
0
90 Days
0
Quality
research- Quality
- medium
- Maturity
- research
Categories
Generative MediaPrimaryOther AI / ML
PM Skills
Developer Platform
Languages
Python100.0%
Timeline
- Project created
- Nov 8, 2018
- Forked
- Mar 14, 2026
- Your last push
- 2 years ago
- Upstream last push
- 2 years ago
- Tracked since
- Oct 19, 2023
Similar Repos
pgvector cosine similarity · $0
Loading…