Ecosyste.ms: Repos
An open API service providing repository metadata for many open source software ecosystems.
GitHub / keonlee9420 / Comprehensive-E2E-TTS
A Non-Autoregressive End-to-End Text-to-Speech (text-to-wav), supporting a family of SOTA unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate E2E-TTS
JSON API: https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keonlee9420%2FComprehensive-E2E-TTS
Stars: 136
Forks: 19
Open Issues: 4
License: None
Language: Python
Repo Size: 3.45 MB
Dependencies:
24
Created: about 2 years ago
Updated: 7 months ago
Last pushed: almost 2 years ago
Last synced: 7 months ago
Topics: deep-learning, end-to-end, fastspeech2, hifi-gan, jets, multi-speaker, neural-tts, non-ar, non-autoregressive, pytorch, single-speaker, sota, speech-synthesis, text-to-speech, text-to-wav, tts, ultimate-tts, unsupervised
Files
Dependencies
- PyYAML ==5.4.1
- g2p-en ==2.1.0
- inflect ==4.1.0
- librosa ==0.7.2
- matplotlib ==3.2.2
- numba ==0.48
- numpy ==1.19.2
- pandas ==1.1.5
- pillow ==8.3.2
- praat-parselmouth ==0.4.1
- pycwt ==0.3.0a22
- pypinyin ==0.39.0
- python_speech_features ==0.6
- pyworld ==0.3.0
- scikit-learn ==0.23.2
- scipy ==1.5.0
- soundfile ==0.10.3.post1
- tensorboard ==2.5
- tensorflow ==2.5.1
- tgt ==1.4.4
- torch ==1.7.0
- torchaudio ==0.7.0
- tqdm ==4.46.1
- unidecode ==1.1.1