feat(core): add ModelScope support for TTS and new office load status

Add support to download and load TTS model from ModelScope, with a fallback to the HuggingFace mirror.
Implement a `documentLoadStatus` property and helper functions in `office.js` to track file loading state.
Improve request cancellation logic in `api.js`, ensuring proper cancel URL resolution and request‑id handling.

These changes enhance robustness, reduce external dependencies, and provide better UX for office file handling.

This commit is contained in:

ydy0615

2026-04-11 10:04:34 +08:00

parent d8b7832b14

commit f99acf5d50

5 changed files with 248 additions and 186 deletions

backend/requirements.txt

View File

@@ -8,6 +8,7 @@ torchaudio>=0.12.0
 transformers>=4.25.0
 whisper>=1.0.0
 qwen-tts>=0.0.0
 modelscope>=1.20.0
 # testing
 pytest>=7.0.0