jasonppy Goto Github PK

academicpages

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

cs61bspring2018

fast-vgs-family

Transformer-based visually grounded speech models

hero_video_feature_extractor

Video Feature Extraction Code for EMNLP 2020 paper "HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training"

jasonppy.github.io

mae-ast-public

Public Code for the paper MAE-AST: Masked Autoencoding Audio Spectrogram Transformer

moment_detr

[NeurIPS 2021] Moment-DETR code and QVHighlights dataset

para-nmt-50m

Pre-trained models and code and data to train and use models from "Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations"

promptingwhisper

Promting Whisper for Audio-Visual Speech Recognition, Code-Switched Speech Recognition, and Zero-Shot Speech Translation

syllable-discovery

Syllable Segmentation and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model

voicecraft

Zero-Shot Speech Editing and Text-to-Speech in the Wild

voicecraft_web

vqwordseg

Unsupervised phone and word segmentation using dynamic programming on self-supervised VQ features.

word-discovery

Word Discovery in Visually Grounded, Self-Supervised Speech Models

yt-dl

zerospeech2021_baseline

BERT and LSTM baseline models of the ZeroSpeech Challenge 2021