sil-ai/tts-singlish
TTS for Singlish using Tacotron2, the IMDA corpus, and Pachyderm.
This project offers a complete workflow to create your own custom text-to-speech (TTS) model for Singlish. You input audio recordings and transcripts from the IMDA National Speech Corpus, and it outputs a fine-tuned TTS model capable of generating spoken Singlish from text. This is ideal for content creators, educators, or businesses looking to create natural-sounding Singlish audio for various applications.
No commits in the last 6 months.
Use this if you need to generate high-quality, synthetic speech in Singlish and have access to the IMDA National Speech Corpus data.
Not ideal if you need a TTS model for a language other than Singlish, or if you don't have access to the specific IMDA National Speech Corpus.
Stars
11
Forks
3
Language
Python
License
—
Category
Last pushed
Jan 11, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/sil-ai/tts-singlish"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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。
shivammehta25/Matcha-TTS
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
coqui-ai/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
DigitalPhonetics/IMS-Toucan
Controllable and fast Text-to-Speech for over 7000 languages!
gabrielmittag/NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment