Commit Graph

58 Commits

Author SHA1 Message Date
jhqxxx 901324cd1a fix qwen3vl-thinking startswith bug 2026-01-31 18:57:42 +08:00
jhqxxx 53791efa80 fix modelscope fun-asr-nano-2512 model load error 2026-01-17 13:18:26 +08:00
jhqxxx d9b803d27e add qwen3 and fun-asr-nano 2026-01-15 21:57:12 +08:00
jhqxxx 461eed7556 updata resample use rubato 2026-01-09 16:06:04 +08:00
jhqxxx 24194182fc update get audio data 2026-01-08 19:22:21 +08:00
jhqxxx d5ec315150 Merge branch 'pr/KingBright/13' 2026-01-08 00:12:23 +08:00
jhqxxx 618d75b263 merge pr/KingBright/13 2026-01-08 00:04:24 +08:00
jhqxxx 6ef8facfde add glm-asr-nano 2026-01-07 21:46:01 +08:00
KingBright 4e35866a59 dynamic home dir & model donwload script 2026-01-05 15:21:15 +08:00
jhqxxx 981457347a load audio has problem 2025-12-31 17:39:25 +08:00
jhqxxx 88ee303392 merge pr/guobin211/12 2025-12-26 00:23:14 +08:00
jhqxxx 9a4fa636be add image api and audio api 2025-12-25 20:25:52 +08:00
michaelbguo 7c9261567b refactor: 为RMBG2.0测试方法添加cfg(test)属性,优化extract_image_url函数避免clone 2025-12-25 10:44:32 +08:00
michaelbguo f35631157a feat: 优化RMBG2.0图像处理性能,支持并行批量处理 2025-12-24 21:42:05 +08:00
jhqxxx bf53d3d869 update fmt 2025-12-24 16:03:39 +08:00
jhqxxx 68e333a4f4 delete test png 2025-12-23 23:47:20 +08:00
jhqxxx 06bd7fce04 add RMBGv2.0 2025-12-23 19:23:21 +08:00
jhqxxx b3c6219e93 update fmt 2025-12-11 23:37:47 +08:00
jhqxxx 855d0cf975 update fmt 2025-12-11 23:30:07 +08:00
jhqxxx d282a0cf40 Merge branch 'voxcpm1.5' 2025-12-11 23:15:05 +08:00
jhqxxx b9947a6516 update voxcpm code to support voxcpm1.5 model 2025-12-11 23:14:43 +08:00
jhqxxx 6430338e95 add url crate to handle local path 2025-12-11 19:33:30 +08:00
jhqxxx 963924a1f1 stash save 2025-12-11 18:33:35 +08:00
jhqxxx 0dc2840b0e update fmt 2025-12-10 16:52:57 +08:00
jhqxxx a67298dc5d Merge branch 'fix_tool_call' 2025-12-10 16:44:40 +08:00
jhqxxx 1a0df13bc7 model test add tps 2025-12-10 16:44:20 +08:00
jhqxxx 567cd70038 update some note 2025-12-10 13:06:53 +08:00
jhqxxx 3eb983b5bb stash save 2025-12-10 12:57:24 +08:00
jhqxxx 515d6da852 replace some function 2025-12-10 00:05:46 +08:00
jhqxxx dc4b593011 add ffmpeg feature 2025-12-09 15:52:26 +08:00
jhqxxx 4228616058 add paddleocr-vl 2025-12-09 00:41:30 +08:00
jhqxxx 697484cf23 add hunyuan_ocr 2025-12-03 17:21:01 +08:00
jhqxxx de3861b731 update note 2025-11-25 17:45:09 +08:00
jhqxxx 08a73bfcc5 deepseek_ocr mes metadata add base_size,image_size,crop_mode 2025-11-24 19:08:01 +08:00
jhqxxx a14c35014a add deepseek_ocr 2025-11-22 23:27:14 +08:00
jhqxxx c95b91ffc0 stash save 2025-11-13 00:33:27 +08:00
jhqxxx c3fa11ed24 temporary save 2025-11-09 15:40:29 +08:00
jhqxxx a5721e7f50 delete not used method 2025-11-04 12:22:02 +08:00
jhqxxx 082bf544d8 update cu_seqlens_repeat 2025-11-04 12:01:41 +08:00
jhqxxx b42c5c718c delete some note 2025-11-02 21:34:43 +08:00
jhqxxx cff51418c7 fix vision data t dim not divisible by temporal_patch_size 2025-10-28 14:29:12 +08:00
jhqxxx 86103fde73 update readme 2025-10-27 13:13:47 +08:00
jhqxxx 1dcccf5aeb update dependences 2025-10-27 10:55:40 +08:00
jhqxxx 86e814708a update video with image 2025-10-26 23:19:11 +08:00
jhqxxx 0e4ca66aca update code format 2025-10-26 21:57:53 +08:00
jhqxxx 7b190e7d54 add Qwen3VL model 2025-10-26 21:39:23 +08:00
jhqxxx bbff5d0601 merge pr 2025-10-15 23:34:23 +08:00
Yijun Zhao 9b9a8f2c73 unify cargo version and add some ci rules 2025-10-15 21:03:49 +08:00
jhqxxx 0fd3c7d935 delete some use 2025-10-14 20:42:03 +08:00
jhqxxx c8cfda7ac4 fix mask bug 2025-10-11 13:14:51 +08:00