shiguredo / lyra-wasm
Lyra V2 WebAssembly build
☆29Updated 6 months ago
Alternatives and similar repositories for lyra-wasm:
Users that are interested in lyra-wasm are comparing it to the libraries listed below
- A javascript library that enables encoding and decoding of audio with Lyra, a neural audio codec.☆21Updated 2 years ago
- A demo of Lyra neural audio codec running on a web browser.☆27Updated 2 years ago
- A fork of Lyra (version 1) that supports a webassembly build. See https://github.com/mayitayew/soundstream-wasm for a more recent version…☆25Updated 2 years ago
- A fork of Lyra V2 (a low-bitrate neural audio codec) that supports a webassembly build.☆27Updated 2 years ago
- Lyra V2 (SoundStream) running in the browser☆19Updated last year
- An echo cancellation library for browsers using DTLN-aec☆26Updated last year
- Nue-ASR inference code by rinna Co., Ltd.☆31Updated 8 months ago
- 44100Hz日本語音源に対応した PITS: Variational Pitch Inference for End-to-end Pitch-controllable TTS without External Pitch Predictor です。☆19Updated last year
- Robust Speech Recognition via Large-Scale Weak Supervision☆19Updated 2 years ago
- ☆21Updated 2 years ago
- An unofficial PyTorch implementation of the StreamVC(Real-Time Low-Latency Voice Conversion)☆119Updated 7 months ago
- Real-time end-to-end singing voice convertion☆20Updated 4 months ago
- Audio Signal Processing by WebAssembly (WAT: WebAssembly Text format and C++ with Emscripten)☆21Updated this week
- (WIP) A retrain of F5-TTS on permissively-licensed data☆10Updated 2 weeks ago
- VITS2 using Phoneme-Level Japanese BERT☆13Updated last year
- Wasm Port of Recurrent neural network for audio noise reduction. Based on xiph/rnnoise C++ project☆42Updated 4 years ago
- Create modular, cross-browser, web audio pipelines to record and process audio in background threads. Comes with modules for VAD, ASR, re…☆47Updated last year
- An unofficial pytorch implementation of "STREAMVC: REAL-TIME LOW-LATENCY VOICE CONVERSION".☆63Updated 8 months ago
- 44100Hz日本語音源に対応した MB-iSTFT-VITS: Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Tim…☆36Updated last year
- Non Parallel Voice Conversion based on VITS☆24Updated last year
- Japanese text preprocessor for Text-to-Speech applications (OpenJTalk rewrite in rust language)☆39Updated this week
- low latency player used Breakout box☆27Updated 2 years ago
- Conformer block with Rotary Position Embedding, modified from lucidrains' implement☆12Updated 6 months ago
- Voice activity detection (VAD) library, based on WebRTC's VAD engine built to WASM with Emscripten to run in browsers, Node, and NativeSc…☆29Updated 8 months ago
- Unofficial implementation of wavenext vocoder☆42Updated 7 months ago
- a cpp ggml port of "VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech." for use in mobile…☆39Updated 7 months ago
- 44100Hz日本語HuBERTに対応した QuickVC: Any-to-many Voice Conversion Using Inverse Short-time Fourier Transform for Faster Conversion です。☆14Updated last year
- [Early Alpha] A unified framework for text-to-speech, voice conversion, automatic speech recognition, audio classification, voice activit…☆21Updated 2 months ago
- Zstandard for browser, Node.js and Deno☆126Updated last week
- ☆8Updated 7 months ago