jumon

whisper-punctuator. Zero-shot multimodal punctuation insertion and truecasing using Whisper

speechbox. Python

whisper-finetuning. [WIP] Scripts for fine-tuning Whisper

react-player. A React component for playing a variety of URLs, including file paths, YouTube, Facebook, Twitch, SoundCloud, Streamable, Vimeo, Wistia and DailyMotion

zac. Zero-shot Audio Classification using Whisper

himitsu. An official implementation of the paper "Addressing Segmentation Ambiguity in Neural Linguistic Steganography"

ocw-central-backend. Source code for the backend of ocwcentral.com

c_nc. Python

ocw-central-frontend. Frontend implementation of ocwcentral.com

whisper. Robust Speech Recognition via Large-Scale Weak Supervision

speech-to-text-benchmark. speech to text benchmark framework

espnet-1. End-to-End Speech Processing Toolkit

steganography-with-masked-lm. Implementation of "Frustratingly Easy Edit-based Linguistic Steganography with a Masked Language Model"

minnn-assignment. An assignment on creating a minimalist neural network toolkit for CS11-747

wtfpython. What the f*ck Python? 😱

mlm-scoring. Python library & examples for Masked Language Model Scoring (ACL 2020)

pywer. A simple Python package to calculate word error rate (WER).

speech-recognition-papers. Towards hot directions in industrial end to end speech recognition

math_writing. Introduction to mathematical writing for undergraduate students majoring in engineering

NLP-progress. Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

speech. A PyTorch Implementation of End-to-End Models for Speech-to-Text

gpu-monitor. Script to remotely check GPU servers for free GPUs

espnet. End-to-End Speech Processing Toolkit

tech-interview-handbook. Curated coding interview preparation materials for busy software engineers

wer_are_we. Attempt at tracking states of the arts and recent results (bibliography) on speech recognition.

pytorch-optimizer. torch-optimizer -- collection of optimizers for Pytorch

Conference-Acceptance-Rate. Acceptance rates for the major AI conferences

100-nlp-papers. 100 Must-Read NLP Papers

fastapi. FastAPI framework, high performance, easy to learn, fast to code, ready for production

scikit-learn. scikit-learn: machine learning in Python

vsrocq. Visual Studio Code extension for Rocq

isucon9-qualify. ISUCON9予選