Search Results for "ai audio" - Page 5

Automatic YouTube subtitle generation is a command-line tool that combines YouTube downloading capabilities with AI-powered transcription using Whisper models. It allows users to download videos or audio from YouTube and automatically generate subtitles or transcripts. The tool processes media locally, extracting audio and applying speech recognition to produce accurate text outputs. It supports multiple languages and can handle different Whisper model sizes, balancing performance and accuracy. yt-whisperc is designed for automation, enabling batch processing of multiple videos for transcription workflows. ...

Based on the Disco Diffusion, we have developed a Chinese & English version of the AI art creation software "AI Atelier". We offer both Text-To-Image models (Disco Diffusion and VQGAN+CLIP) and Text-To-Text (GPT-J-6B and GPT-NEOX-20B) as options. Making available complete source code of licensed works and modifications, which include larger works using a licensed work, under the same license. Copyright and license notices must be preserved.

Implementation of NWT, audio-to-video generation, in Pytorch. The paper proposes a new discrete latent representation named Memcodes, which can be succinctly described as a type of multi-head hard-attention to learned memory (codebook) key/values. They claim the need for less codes and smaller codebook dimensions in order to achieve better reconstructions.

AugLy is a data augmentations library that currently supports four modalities (audio, image, text & video) and over 100 augmentations. Each modality’s augmentations are contained within its own sub-library. These sub-libraries include both function-based and class-based transforms, composition operators, and have the option to provide metadata about the transform applied, including its intensity. AugLy is a great library to utilize for augmenting your data in model training, or to evaluate...

Denoiser is a real-time speech enhancement model operating directly on raw waveforms, designed to clean noisy audio while running efficiently on CPU. It uses a causal encoder-decoder architecture with skip connections, optimized with losses defined both in the time domain and frequency domain to better suppress noise while preserving speech. Unlike models that operate on spectrograms alone, this design enables lower latency and coherent waveform output. The implementation includes data...

Eve is a AI project written in python that takes commands verbally or textually to control the computer and eveyday functions.

A simple, yet powerful framework built around the OGRE rendering system. Has many features in the works such as AI, Audio, an entity system (much like CEL), and a complete level editor.

The UIless Playlist Manager intends to be a generic music player, capable of managing multiple playlists based on different criterias, scalable to accomodate the needs of end users. UPM is an experiment in AI-using playlist management technology.

Dia-1.6B is a 1.6 billion parameter text-to-speech model by Nari Labs that generates high-fidelity dialogue directly from transcripts. Designed for realistic vocal performance, Dia supports expressive features like emotion, tone control, and non-verbal cues such as laughter, coughing, or sighs. The model accepts speaker conditioning through audio prompts, allowing limited voice cloning and speaker consistency across generations. It is optimized for English and built for real-time performance...