Commit Graph

201 Commits

Author SHA1 Message Date
jhqxxx 4811693285 update readme 2026-03-24 15:51:42 +08:00
jhqxxx 7d3cd50e35 update fmt 2026-03-23 22:09:20 +08:00
jhqxxx 9224593b78 add LFM2-1.2B, LFM2.5-1.2B-Instruct 2026-03-23 22:07:41 +08:00
jhqxxx 77b244e53e add wechat qrcode 2026-03-19 19:25:29 +08:00
jhqxxx fb37be0dae v0.2.3 2026-03-19 17:24:08 +08:00
jhqxxx adeea15a12 update description 2026-03-18 22:30:45 +08:00
jhqxxx 6890f86030 add deepseek-ocr2 support 2026-03-18 19:15:21 +08:00
jhqxxx ca57a7245c update docs 2026-03-17 21:35:54 +08:00
jhqxxx 55a5007c07 add PaddleOCR-VL1.5 support 2026-03-17 21:30:50 +08:00
jhqxxx fb4a50f745 cli add about gguf param 2026-03-17 15:39:34 +08:00
jhqxxx 80d36b5308 add Qwen3.5 mmproj gguf 2026-03-16 14:50:59 +08:00
jhqxxx 9c9275b767 api add /v1/ 2026-03-14 23:10:40 +08:00
jhqxxx 813f4decaf update fmt 2026-03-14 20:23:07 +08:00
jhqxxx 21caee0522 update fmt 2026-03-14 20:06:20 +08:00
jhqxxx 0c6d4d01d9 Merge branch 'pr/Tsai002/38' 2026-03-14 19:30:33 +08:00
jhqxxx d0cbd0c90e Merge branch 'add_model' 2026-03-14 19:27:26 +08:00
jhqxxx aad0e62151 add qwen3.5 gguf 2026-03-14 19:27:01 +08:00
Wei Cai 83d6c0b480 Merge pull request #1 from jhqxxx/main
sync upstream
2026-03-12 12:02:11 +08:00
github 1905aecae0 fix #34 2026-03-11 22:37:39 +08:00
jhqxxx 4d544ab68f from gguf build chat_template and tokenizer 2026-03-11 17:30:28 +08:00
XiaoYang 8ec2ef6ad3 fmt: format code according to rustfmt standards 2026-03-10 21:45:04 +08:00
XiaoYang 2f452ab925 feat(cli): add model download verification and update model listing output(cli/json) 2026-03-10 21:34:03 +08:00
XiaoYang e66ff27288 docs(api): add audio transcription API documentation 2026-03-10 21:34:03 +08:00
jhqxxx 86141322bb update chat_template.jinja load 2026-03-08 21:20:24 +08:00
jhqxxx 20b5260633 update fmt 2026-03-07 18:09:29 +08:00
jhqxxx d2524d6a19 merge glm-ocr model 2026-03-07 18:08:06 +08:00
jhqxxx cf308f93eb Merge branch 'pr/jasonzou/31' 2026-03-07 14:25:44 +08:00
jason 1fe06110ff more glm-ocr tweaks 2026-03-06 11:25:44 -05:00
jhqxxx 2ef86b5a88 generate remove unnecessary code 2026-03-06 19:40:39 +08:00
jhqxxx 037207eccd update generate param init 2026-03-06 19:08:58 +08:00
jhqxxx 548eb8185e usage add prompt_tokens 2026-03-06 18:38:16 +08:00
jhqxxx 2d37efaab6 update fmt 2026-03-06 17:28:08 +08:00
jhqxxx 8ada86714c fix load_image_from_url blocking bug 2026-03-06 15:50:43 +08:00
jhqxxx 598a16921c Merge branch 'pr/go-restream/29' 2026-03-06 14:52:01 +08:00
jason 3156818a0c glm-ocr 2026-03-05 23:49:49 -05:00
jhqxxx 9a09b998a6 fix qwen3.5-9b config bug 2026-03-06 12:31:00 +08:00
jhqxxx f482bf1a54 update qwen3.5 only text conpute pos bug 2026-03-06 12:14:18 +08:00
XiaoYang b559376438 feat(asr): add text response format support and improve code formatting 2026-03-06 12:00:39 +08:00
XiaoYang 63a89b0c96 feat(api): add OpenAI-compatible ASR transcription endpoint
- Implement POST /audio/transcriptions and /v1/audio/transcriptions
  endpoints for automatic speech recognition
- Add support for multipart/form-data audio file uploads
- Support multiple audio formats (wav, mp3, m4a, etc.)
- Implement language detection with 29 supported languages
- Return transcription text in OpenAI-compatible JSON format
- Add proper error handling and validation
- Include comprehensive tests for ASR functionality

refactor(api): restructure API modules and export MODEL

- Move API declarations to src/api/mod.rs
- Add ASR module and type definitions
- Export MODEL static for use in ASR module
- Mount ASR routes at both /audio and /v1/audio endpoints
2026-03-06 11:41:32 +08:00
jhqxxx 14ecd4676c update aha_openai_dive::v1::resources::chat pub 2026-03-05 22:27:17 +08:00
jhqxxx b2a687a05e update fmt 2026-03-05 21:59:38 +08:00
jhqxxx 4ae8b0b2f4 add Qwen3.5 model 2026-03-05 21:57:03 +08:00
jhqxxx a61b899741 update interpolate 2026-03-01 12:44:14 +08:00
jhqxxx 6a73ee04c3 update candle version 0.9.2 2026-02-24 16:34:06 +08:00
jhqxxx e19c1d0744 update cargo.toml description 2026-02-14 16:56:38 +08:00
jhqxxx 309025edb0 update version 2026-02-14 16:53:15 +08:00
jhqxxx 9dfe60cb53 update fmt 2026-02-14 16:46:09 +08:00
jhqxxx 28f8fb6c1b update fmt 2026-02-14 16:34:12 +08:00
jhqxxx b77676f029 delete index-ttss 2026-02-14 16:06:50 +08:00
jhqxxx 2c34fc2d79 updata index tts 2026-02-14 15:52:30 +08:00