israelg99/deepvoice
Deep Voice: Real-time Neural Text-to-Speech
Implements a modular five-stage pipeline: grapheme-to-phoneme conversion via bidirectional GRU encoder-decoder with beam search, phoneme segmentation using Deep Speech 2-style convnet-RNN with CTC loss, joint duration and F0 prediction through stacked fully-connected and recurrent layers, and WaveNet-based audio synthesis. Built on Keras with custom modifications for neural vocoding at high sampling rates.
364 stars. No commits in the last 6 months.
Stars
364
Forks
92
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 21, 2017
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/israelg99/deepvoice"
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