Search Results for "state-thread"

LiveAvatar is an open-source research and implementation project that provides a unified framework for real-time, streaming, interactive avatar video generation driven by audio and other control signals. It implements techniques from state-of-the-art diffusion-based avatar modeling to support infinite-length continuous video generation with low latency, enabling interactive AI avatars that maintain continuity and realism over extended sessions. The project co-designs algorithms and system optimizations, such as block-wise autoregressive processing and fast sampling strategies, to deliver real-time frame rates (e.g., ~45 FPS on appropriate GPU clusters) while handling non-stop generation without quality degradation. ...

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec. Mimi processes 24 kHz audio, down to a 12.5 Hz representation with a bandwidth of 1.1 kbps, in a fully streaming manner (latency of 80ms, the frame size), yet performs better than existing, non-streaming, codecs like SpeechTokenizer (50 Hz, 4kbps), or SemantiCodec (50 Hz, 1.3kbps). Moshi models two streams of audio: one corresponds to Moshi, and the other one to the user. ...

Encodec is a neural audio codec developed by Meta for high-fidelity, low-bitrate audio compression using end-to-end deep learning. Unlike traditional codecs (like MP3 or Opus), Encodec uses a learned quantizer and decoder to reconstruct complex waveforms with remarkable accuracy at bitrates as low as 1.5 kbps. It employs a convolutional encoder–decoder architecture trained with perceptual loss functions that optimize for human auditory quality rather than raw waveform distance. The model can...

Spleeter is the Deezer source separation library with pretrained models written in Python and using Tensorflow. It makes it easy to train music source separation models (assuming you have a dataset of isolated sources), and provides already trained state of the art models for performing various flavours of separation. 2 stems and 4 stems models have state of the art performances on the musdb dataset. Spleeter is also very fast as it can perform separation of audio files to 4 stems 100x faster than real-time when run on a GPU. We designed Spleeter so you can use it straight from command line as well as directly in your own development pipeline as a Python library. ...

BTK contains C++ and Python libraries that implement speech processing and microphone array techniques such as speech feature extraction, speech enhancement, speaker tracking, beamforming, dereverberation and echo cancellation algorithms. The Millennium ASR provides C++ and python libraries for automatic speech recognition. The Millennium ASR implements a weighted finite state transducer (WFST) decoder, training and adaptation methods. These toolkits are meant for facilitating research and development of automatic distant speech recognition.