Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".

This repository collects an extensive list of awesome papers about Story Generation / Storytelling, primarily focusing on the era of Large Language Models (LLMs).

Generate interleaved text and image content in a structured format you can directly pass to downstream APIs.

Groq-powered chat assistant for generating contextual responses to user queries.

Scripts for computing the Intelligibility and CLVP scores for evaluating TTS models

The Programmable Cypher-based Neuro-Symbolic AGI that lets you program its behavior using Graph-based Prompt Programming: for people who want AI to behave as expected

Infinite Alchemy is an AI-powered game where you mix and match elements to create basically anything

Comparison of Language Model Inference Engines

EMNLP 23 - Integrating Whisper Encoder to LLaMA Decoder for Generative ASR Error Correction

Awesome speech/audio LLMs, representation learning, and codec models

Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple

whiteboard / infinite canvas SDK

draw.io is a JavaScript, client-side editor for general diagramming.

A python package to analyze and compare voices with deep learning

A repository for publicly/freely available Natural Language Processing (NLP) datasets for African languages.

Inference Llama 2 in one file of pure C

A multi-voice TTS system trained with an emphasis on quality

A generative language model which seeks to maximize rhyming syllables. Based on OpenAI's GPT-2.

VTuber application which only requires your voice and microphone, no need for a webcam or other tracking nonsense.

OrgChart with a twist! Simpler, faster navigation and exporting capabilities for those power users who need to manage bulky organizations.

A browser extension that removes YouTube suggestions, comments, shorts, and more

Self-Supervised Speech Pre-training and Representation Learning Toolkit

Phoneme Recognition using pre-trained models Wav2vec2, HuBERT and WavLM. Throughout this project, we compared specifically three different self-supervised models, Wav2vec (2019, 2020), HuBERT (2021…

Repository for fine-tuning Transformers 🤗 based seq2seq speech models in JAX/Flax.

PyTorch code for “TVLT: Textless Vision-Language Transformer” (NeurIPS 2022 Oral)

AfriBERTa: Exploring the Viability of Pretrained Multilingual Language Models for Low-resourced Languages

Genetic programming using the Elixir AST

Library for Textless Spoken Language Processing

THIS REPO IS NOT MAINTAINED ANYMORE. Please see https://codeberg.org/tenacityteam/tenacity for Tenacity, which is maintained.