131 Commits (f663f420c42b263088f0ce28219d8389b1662f80)

Author SHA1 Message Date
  wenmeng.zwm 4dd99b8f6e Revert "move opencv dependency from framwork to cv " 2 years ago
  jiangyu.xzy 9bfc77c178 support asr new models 2 years ago
  yichang.zyc ebb9636179 fix 不必要的init和优化vqa的preprocessor 2 years ago
  shiyi.zxh b386a4ee50 adapt to different wav input 2 years ago
  jiangyu.xzy 2b62084146 add funasr based asr inference 2 years ago
  shiyi.zxh 7661470350 ofa增加asr任务 2 years ago
  james.wjg 541e460f8b add support for cv/language_guided_video_summarization 2 years ago
  yingda.chen e970a6eb43 move opencv dependency from framwork to cv 2 years ago
  mulin.lyh 1ca24299da [to #45892407]fix: fix pytorch_lighting incompatible with taming-transformers-rom1504 2 years ago
  mulin.lyh 4429991646 Merge branch dev/msdataset_event_tracking into master 2 years ago
  干劲 aecb88044e up 2 years ago
  干劲 853e5235d5 fix requirements 2 years ago
  干劲 30c8c27145 up requirements 2 years ago
  班扬 79c44a6810 add event tracking 2 years ago
  班扬 84032f90e3 add event tracking 2 years ago
  liugao.lg 40b6770956 [to #42322933]fix ocr prepreocess & conflict 2 years ago
  Yingda Chen 3464324f6b [to #42322933] limit datasets version for now 2 years ago
  wenmeng.zwm e07f3cdbf5 remove fasttext 2 years ago
  Yufeng 261c04b8b5 add Mglm (#5) 2 years ago
  ran.zhou 13f7e9ceca [to #42322933]SEA multilingual NLP (NER & word segmentation) 2 years ago
  yuanzheng.yuanzhen bab54bbce8 [to #42322933]support uni fold 2 years ago
  yichang.zyc 6ddafb3218 [to #42322933]caption finetune done, add belu metric 2 years ago
  mulin.lyh 7257f6c6fb [to #45631658]feat support eas deploy 2 years ago
  shouzhou.bx 01d521dd78 [to #42322933]add face 2d keypoints finetune test case 2 years ago
  shuying.shu cb570d586c add referring video object segmentation pipeline 3 years ago
  zhangzhicheng.zzc 7e7303a658 [to #42322933] remove fasttext from nlp requirements 3 years ago
  Yingda Chen deb847614a [to #42322933] limit espnet version 3 years ago
  hemu 876058556d fix generate 3 years ago
  Yingda Chen 355da866c5 [to #42322933] limit tranformers version temporarily 3 years ago
  wenmeng.zwm 275f8b4323 Revert "[to #45071449] fix setup error " 3 years ago
  bin.xue 3863efc14d [to #42322933] add far field KWS trainer 3 years ago
  wenmeng.zwm 8c91a4972e require pai-easycv 0.6.3.7 3 years ago
  wenmeng.zwm a26e6e3869 [to #45071449] fix setup error 3 years ago
  ashui.cbh 69da8f91ac [to #42322933]suport image inpainting 3 years ago
  ryan.yy ff69439c4f [to #42322933]add image_body_reshaping code 3 years ago
  moyu.wk 42896de709 [to #42322933]add pipelines for APE\QE\Domain Classifications 3 years ago
  wenmeng.zwm 97ffa3a8d2 [to #44902165] update easycv version 3 years ago
  jiaqi.sjq e90ff9e479 [to #42322933] tts sambert am changs from tensorfow to PyTorch and add licenses 3 years ago
  jiangnana.jnn 376ba9fef9 [to #42322933]update easycv pipelines 3 years ago
  zhangzhicheng.zzc c35f8cb42b [to #42322933] remove deepspeed and fariseq from requirments 3 years ago
  suluyan.sly 904374d329 [to #42322933] feat: plug inference 3 years ago
  wenmeng.zwm ba74cdf97e [to #43878347] Rename runtime.txt to framework.txt 3 years ago
  mulin.lyh 9e14d6727b [to #44571845]fix: ci support multiple image 3 years ago
  shuying.shu a9deb3895c [to #42322933] movie scene segmentation模型接入 3 years ago
  xiangpeng.wxp 054151d92f [to #42322933]nlp_translation_preprocess 3 years ago
  jiangnana.jnn 930d55d9ad support EasyCV framework and add Segformer model 3 years ago
  mulin.lyh 01bb751425 [to #43653669]feat: auto build docker images 3 years ago
  feiwu.yfw 35548bd492 [to #43875101] 3 years ago
  bin.xue d0933a2374 [to #42322933] add far field kws model pipeline 3 years ago
  piaoyu.lxy 2dc3286524 [to #42322933] add conversational_text_to_sql pipeline 3 years ago