xcmyz/FastSpeech
The Implementation of FastSpeech based on pytorch.
Implements parallel text-to-speech synthesis using a feed-forward Transformer architecture with a length regulator module, enabling 3x faster training than sequential models. Integrates Tacotron2 for alignment extraction and WaveGlow as a neural vocoder for mel-spectrogram-to-waveform conversion. Optimized for the LJSpeech dataset with hyperparameters aligned to FastSpeech2 specifications.
880 stars. No commits in the last 6 months.
Stars
880
Forks
216
Language
Python
License
MIT
Category
Last pushed
Jul 06, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/xcmyz/FastSpeech"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
yeyupiaoling/MASR
Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。
coqui-ai/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
shivammehta25/Matcha-TTS
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
netease-youdao/EmotiVoice
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
gabrielmittag/NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment