TXH-mercury/VAST
Code and Model for VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset
Jupyter NotebookMIT
Issues
- 0
How to download the videos of VAST 27M?
#29 opened by Molly-3000 - 0
- 1
Inference code
#7 opened by 1980x - 0
How can i download the video?
#27 opened by clawnotfound - 0
Question about table6
#26 opened by wunovation - 4
- 3
- 0
- 1
/github/workspace/src/video/ffmpeg/threaded_decoder.cc:292: [14:29:09] /github/workspace/src/video/ffmpeg/threaded_decode r.cc:218: Check failed: avcodec_send_packet(dec_ctx_.get(), pkt.get()) >= 0 (-11 vs. 0) Thread worker: Error sending packet.
#20 opened by lxslxs1 - 3
- 4
Error about finetune_qa_msvd task (Miss key 'desc' or 'caption' in descs_qa_trainval.json)
#16 opened by BinzheLi95 - 0
Activitynet-QA annotations are missing
#23 opened by poffertje - 0
Problem running finetuning on TGIF
#24 opened by poffertje - 0
- 0
- 0
- 0
Missing config files for pretrain
#13 opened by jiaozizhao - 1
- 1
- 0
- 0
- 0
- 0
Memory usuage during validation
#9 opened by 1980x - 0
Dataset download
#8 opened by rongerAlgo - 11
Code Release Please
#5 opened by YajieW99 - 7
Code release
#4 opened by rose-jinyang - 7
Nice work!
#3 opened by jetwu-create