Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection

The implementation for "Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions"

The official Pytorch implementation of "Frame-wise streaming end-to-end speaker diarization with non-autoregressive self-attention-based attractors". [ICASSP 2024] and "LS-EEND: long-form streaming…

[ICLR 2025] Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes

This repository aims at providing efficient CNNs for Audio Tagging. We provide AudioSet pre-trained models ready for downstream training and extraction of audio embeddings.

VALL-E 2 reproduction

Training code for FAcodec presented in NaturalSpeech3

Structured state space sequence models

Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in Pytorch

LLM101n: Let's build a Storyteller

GPT-SoVITS2

Official code for "MAmmoTH2: Scaling Instructions from the Web" [NeurIPS 2024]

Fine Tune the Style-TTS2 Voice Model

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

Official code for Paper "Mantis: Multi-Image Instruction Tuning" [TMLR 2024]

Scalable data pre processing and curation toolkit for LLMs

A family of lightweight multimodal models.

💌 Template website undangan pernikahan HTML sederhana menggunakan Bootstrap, AOS, Font Awesome, Canvas Confetti, Google Fonts, dan Vanilla JS.

PyTorch native post-training library

https://medium.com/@aimiwen33/exploring-taylor-swifts-music-2bce11a7aab2

practical introduction to Python for machine learning, with pandas and scikit-learn - Sept 2014

Classification problem in machine learning where a Portuguese bank is trying to be able to predict which customers will open a term deposit or not.

A set of scripts and notebooks on LLM finetunning and dataset creation

Query any web document and retrieve concise answers with citations leveraging the power of LangChain's text splitting, embeddings, and vector storage. Built with Python, GPT 3.5, Langchain, and Gra…

Automate web research way beyond the first page of search results; curate knowledge bases to chat with.

Grounded search engine (i.e. with source reference) based on LLM / ChatGPT / OpenAI API. It supports web search, file content search etc.