Lists (5)
Stars
A tiny game engine that lets you share games as URLs
Local computer use on Apple silicon: on-device typed decisions with laya and form filling with CUA-S1-FORMS, driven through the macOS Accessibility API
High-performance, token-based structured data engine for .NET. A core component of REX, the technology behind CAPCOM's next-generation game engine.
Official repository for “GrainSpeech: Less Context, More Detail for Compact Speech Synthesis.”
Emulation of the Drosophila Fly brain: Brian2, Brian2CUDA, PyTorch, NEST GPU, and neuromorphic chips
Fast singing-voice acoustic model: harmonic + noise excitation refined into a mel by a 1-step rectified flow (bundled NHVSing vocoder). Multi-speaker + style control; ONNX export.
CuteTTS: a lightweight continuous autoregressive TTS model that runs efficiently on GPUs, CPUs, and Apple silicon.
Phoneme alignment based on a variational autoencoder (VAE) and self-supervised learning (SSL) acoustic features.
Implementation of RIFT-SVC, a singing voice conversion model based on Rectified Flow Transformer.
We propose LeapTalk, a novel framework that achieves stable and real-time talking-head generation with a single forward step, scaling to arbitrarily long videos.
A Robust Low-Latency Streaming Zero-Shot Voice Conversion
Japanese Braille translator originally developed for NVDAJP
The ConvFill Repository provides training and inference code for the Conversational Infill task proposed and implemented in Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive…
[NAACL 2025] WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matching
Haqumei (薄明/拍命) is a Japanese Grapheme-to-Phoneme (G2P) library.
Training code and dataset cleasing with Sidon
ITA Corpus Emotion: Read Speech Dataset from 50 Speakers — Commercial R&D Use Permitted under the Terms of Use
[Under Review] A Vibrato Controlling Method by Predicting High-frequency F0 contour for Singing Voice Conversion
Causal zero-shot voice conversion at 44.1kHz.
Miso TTS is an 8 billion, highly emotive text-to-speech model
WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling
DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action
First foundation ASR built for the real world - 7 atomic acoustic conditions, 54 compound scenarios, 2.6M samples, and up to ~30% gains over SOTA where every other model falls apart. **You'll come …
Even Realities Hub Simulator - multi application test environment
Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation