hhguo/SoCodec
Ultra-low-bitrate Speech Codec for Speech Language Modeling Applications
SoCodec helps you compress speech audio into extremely small digital codes, allowing for efficient use in advanced text-to-speech systems. It takes in spoken audio (currently Chinese) and converts it into a highly compressed representation, which can then be used to synthesize speech. This is ideal for speech synthesis engineers or researchers working with language models for text-to-speech.
No commits in the last 6 months.
Use this if you need to dramatically reduce the file size of speech audio while maintaining quality for text-to-speech applications based on language models.
Not ideal if you need to process languages other than Chinese, as multi-lingual support is still under development.
Stars
90
Forks
9
Language
Python
License
MIT
Category
Last pushed
Dec 20, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/hhguo/SoCodec"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
kan-bayashi/ParallelWaveGAN
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
fatchord/WaveRNN
WaveRNN Vocoder + TTS
shangeth/wavencoder
WavEncoder is a Python library for encoding audio signals, transforms for audio augmentation,...
rishikksh20/iSTFTNet-pytorch
iSTFTNet : Fast and Lightweight Mel-spectrogram Vocoder Incorporating Inverse Short-time Fourier...
seungwonpark/melgan
MelGAN vocoder (compatible with NVIDIA/tacotron2)