🌱 a curated list of tools to help you with your research/life; I built a front end around this repo, please use the link below [This repo is Not Maintained Anymore]

The official repository of Dynamic-SUPERB.

Efficient implementations of Needleman-Wunsch and other sequence alignment algorithms written in Rust with Python bindings via PyO3.

Artie Bias Corpus: an audio corpus + code for detecting demographic bias

MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

Noise supression using deep filtering

DDSP: Differentiable Digital Signal Processing

Machine Learning Engineering Open Book

Collection of audio-focused loss functions in PyTorch

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Multilingual Voice Understanding Model

[NeurIPS'23 Spotlight] "Mind2Web: Towards a Generalist Agent for the Web"

A one stop repository for generative AI research updates, interview resources, notebooks and much more!

🤗 AutoTrain Advanced

Olive is an easy-to-use hardware-aware model optimization tool that composes industry-leading techniques across model compression, optimization, and compilation.

PyTorch implementation of Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities.

💯 Curated coding interview preparation materials for busy software engineers

Portable package manager for Neovim that runs everywhere Neovim runs. Easily install and manage LSP servers, DAP servers, linters, and formatters.

Pythonic framework for building ONNX graphs

Whisper fine-tuning event script to use multiple hf datasets

Whisper finetuned on VinBigdata-VLSP2020-100h + KenLM

[WIP] Scripts for fine-tuning Whisper

Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets or datasets from huggingface.

Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deplo…

Whisper realtime streaming for long speech-to-text transcription and translation

An evolving, large-scale and multi-domain ASR corpus for low-resource languages with automated crawling, transcription and refinement

Collection of scripts from mHuBERT-147.