liuhuang31 / g2pw_onceLinks
G2pw's inference speed is accelerated by about 8-10 times. Change loop generated predictive data to only once and model loop prediction becomes only once.
☆14Updated last year
Alternatives and similar repositories for g2pw_once
Users that are interested in g2pw_once are comparing it to the libraries listed below
Sorting:
- ☆25Updated 2 years ago
- ☆19Updated 2 years ago
- Try to replicate the architecture of MiniMaxTTS mentioned in it's technical report☆48Updated last month
- Just another FastSpeech 2 but cleaner code :)☆27Updated last year
- ☆23Updated 4 months ago
- ☆19Updated last year
- ☆39Updated 2 years ago
- Unofficial pytorch implementation of VISinger: Variational Inference with Adversarial Learning for End-to-end Singing Voice Synthesis (IC…☆17Updated 2 years ago
- DiFlow-TTS: Compact and Low-Latency Zero-Shot Text-to-Speech with Factorized Discrete Flow Matching☆56Updated 3 weeks ago
- text to speech☆10Updated last year
- The source code for the paper CrossSinger (asru2023)☆18Updated 2 years ago
- E2E TTS using Conditional Flow Matching (Experimental*)☆71Updated last year
- (WIP)long form speech generatoins☆31Updated 6 months ago
- Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge☆21Updated 3 years ago
- Adaptive Vocoder for Custom Voice☆60Updated 3 years ago
- LIGHTVOC AN UPSAMPLING-FREE GAN VOCODER BASED ON CONFORMER AND INVERSE SHORT-TIME FOURIER TRANSFORM☆18Updated last year
- ☆23Updated last year
- ☆26Updated 3 years ago
- (R&D) Text to speech using phonemes as inputs and audio codec codes as outputs. Loosely based on MegaByte, VALL-E and Encodec.☆48Updated 2 years ago
- A pitch detection model trained to be robust against noise and reverberation environments.☆27Updated 9 months ago
- ☆45Updated 2 years ago
- ☆14Updated 11 months ago
- [ACMMM'2024] Generative Expressive Conversational Speech Synthesis☆40Updated 11 months ago
- ☆33Updated 2 years ago
- ☆25Updated last year
- Unofficial Pytorch implementation of SNAC: Speaker-normalized affine coupling layer in flow-based architecture for zero-shot multi-speake…☆57Updated 2 years ago
- Automatic speech annotator processing speech with voice activaty detection, overlapping speech detection, speaker diarization and automat…☆33Updated last year
- Official implementation of "Unsupervised Pre-training for Data-Efficient Text-to-Speech on Low Resource Languages", ICASSP 2023☆27Updated 2 years ago
- Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale☆27Updated 2 years ago
- CML-TTS: A Multilingual Dataset for Speech Synthesis☆33Updated last year