37 8 15

Joshua Nemecek

jnemecek

https://www.buymeacoffee.com/DCNemesis

AI & ML interests

NLP for low resource languages

Recent Activity

new activity 2 days ago

UNESCO/nllb:Commercial use?

commented on a paper 24 days ago

Magic 1-For-1: Generating One Minute Video Clips within One Minute

authored a paper 3 months ago

Bloom Library: Multimodal Datasets in 300+ Languages for a Variety of Downstream Tasks

View all activity

Organizations

jnemecek's activity

New activity in UNESCO/nllb 2 days ago

Commercial use?

#12 opened 2 days ago by

jnemecek

commented a paper 24 days ago

Magic 1-For-1: Generating One Minute Video Clips within One Minute

Paper • 2502.07701 • Published 26 days ago • 34 •

New activity in bible-nlp/biblenlp-corpus 3 months ago

Getting error 36

#5 opened over 1 year ago by

sakthi07

Convert name keyword argument to an md5 hash

#10 opened 11 months ago by

ajland

commented a paper 5 months ago

Differential Transformer

Paper • 2410.05258 • Published Oct 7, 2024 • 171 •

New activity in tencent/MimicMotion 6 months ago

Not Open Source?

#2 opened 6 months ago by

jnemecek

commented a paper 6 months ago

MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance

Paper • 2406.19680 • Published Jun 28, 2024 • 1 •

commented 2 papers 7 months ago

PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation

Paper • 2408.07547 • Published Aug 14, 2024 • 8 •

BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation

Paper • 2407.17952 • Published Jul 25, 2024 • 31 •

New activity in sil-ai/wav2vec2-bloom-speech-sdk 12 months ago

License link is dead

#1 opened 12 months ago by

Lechasseur

New activity in bible-nlp/biblenlp-corpus about 1 year ago

[Suggestion] Parquet

#6 opened over 1 year ago by

christopher

Difference between this dataset and the OPUS version?

#7 opened about 1 year ago by

ZhaofengWu

commented a paper about 1 year ago

BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data

Paper • 2402.08093 • Published Feb 12, 2024 • 60 •

New activity in bible-nlp/biblenlp-corpus over 1 year ago

corpus.json doesn't contain all the txt files

#4 opened over 1 year ago by

charlie0608

New activity in sil-ai/bloom-lm over 1 year ago

Shipibo

#6 opened over 1 year ago by

Eklavya

New activity in sil-ai/bloom-speech about 2 years ago

load_dataset function returns an error

#3 opened about 2 years ago by

idar

New activity in woz4tetra/charged_up_2023 about 2 years ago

Labels aren't showing up

#1 opened about 2 years ago by

jnemecek

New activity in sil-ai/bloom-speech over 2 years ago

Problem loading data with datasets==2.7

#1 opened over 2 years ago by

cassiepowell

Fix for datasets 2.7

#2 opened over 2 years ago by

lhoestq

New activity in sil-ai/audio-keyword-spotting over 2 years ago

Fix task tags

#2 opened over 2 years ago by

albertvillanova