Highlights
- Pro
Lists (1)
Starred repositories
A high-throughput and memory-efficient inference and serving engine for LLMs
Efficient Triton Kernels for LLM Training
An open source implementation of CLIP.
Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, Du…
Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.
[Official Implementation] Acoustic Autoregressive Modeling 🔥
A list of publicly available room impulse response datasets and scripts to download them.
Evaluation Protocol for Large-Scale Zero-Shot TTS Literature
A sequence-to-sequence voice conversion toolkit.
PyTorch reimplementation of the DiracGAN proposed in the paper "Which Training Methods for GANs do actually Converge?" [ICML 2018].
Enjoy the magic of Diffusion models!
The open source code for SimpleSpeech series
Reading list for research topics in Sound AI
Source for the Interspeech 2024 Paper "Scaling up masked audio encoder learning for general audio classification"
A paper collection of recent diffusion models for text-image generation tasks, e,g., visual text generation, font generation, text removal, text image super resolution, text editing, handwritten ge…
PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838
The official Implementation of PeriodWave and PeriodWave-Turbo
A curated list of reinforcement learning with human feedback resources (continually updated)
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
📖 A curated list of resources dedicated to talking face.
The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.
[ACM MM 2024] This is the official code for "AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding"
Automatically Update Text-to-speech (TTS) Papers Daily using Github Actions (Update Every 12th hours)
real time face swap and one-click video deepfake with only a single image
JS tokenizer for LLaMA 3 and LLaMA 3.1