Search Results for "python neural"

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...

...It includes MusicGen for music generation conditioned on text (and optionally melody) and AudioGen for text-conditioned sound effects and environmental audio. Both models operate over discrete audio tokens produced by a neural codec (EnCodec), which acts like a tokenizer for waveforms and enables efficient sequence modeling. The repo provides inference scripts, checkpoints, and simple Python APIs so you can generate clips from prompts or incorporate the models into applications. It also contains training code and recipes, so researchers can fine-tune on custom data or explore new objectives without building infrastructure from scratch. ...

VCClient is a real-time voice conversion system that uses machine learning models to transform a speaker’s voice into another voice with minimal latency. It is designed for live applications such as streaming, gaming, and virtual communication, where immediate feedback is essential. The system supports multiple voice conversion models, including RVC and other neural network-based approaches, allowing users to switch between different voices or customize their output. It provides both a...

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...

RNNLIB is a recurrent neural network library for sequence learning problems. Applicable to most types of spatiotemporal data, it has proven particularly effective for speech and handwriting recognition. full installation and usage instructions given at http://sourceforge.net/p/rnnl/wiki/Home/

oddioToolz (oz) aims to be a modular audio IDE geared toward realtime audio synthesis, manipulation, quantization, sequencing, interaction and the exchange of sound/modules/meta over computer and neural networks worldwide. oz needs help e-mail a dev!