支持DirectML等其他ONNX能识别的后端使用GPU加速执行 - #380
Merged
Merged
Conversation
Contributor
Author
eritpchy
force-pushed
the
patch-23
branch
2 times, most recently
from
March 6, 2025 11:20
7ac2a8a to
47af225
Compare
eritpchy
force-pushed
the
patch-23
branch
2 times, most recently
from
March 6, 2025 13:16
3bd38fa to
ec01d22
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.

以下部分经过小程序线上大量验证
✅使用官方的PaddleOCR (2.9.1), 跟随官方线上更新
✅支持DirectML for windows(基于ONNX),让其他独显集显(比如Intel/AMD/其他)也能高速处理字幕,实测在快速/自动模式下RyzenAI PC集显效率>=Nvidia 20系独立显卡效率
✅基于ONNX,同步支持AMD ROCm(Windows环境部署太过苛刻,需要Linux)
✅升级至Paddle 3.0.0rc1
✅修复识别性能问题,移除2行无效的代码,来自#372
✅完善相关文档说明
✅主界面标题显示版本号,方便定位问题
✅由于PySimpleGUI作者故意移除免费的旧版本,改用PySimpleGUI-4-foss,已计划抛弃
以上内容在Windows 11(RyzenAI PC) 以及 Windows 10 (CUDA 10.2/11.8/12.3) 测试通过
合并这个PR请优先合并#379
完,可以使用CI打出来的整合包进行测试 https://github.com/eritpchy/video-subtitle-extractor/releases
PS: 根据Github政策,开源项目可以大量使用Action不会产生额外扣费, 详见: 使用限制、计费和管理以及Plans and usage, 同时设置Spending Limit 也是非常有必要的
PS: 往后发布版本请先修改config.py里面的版本号再做提交,否则CI会将已发布版本的TAG给覆盖,为了避免手误覆盖TAG也可以手动启用每个action里面的“检查 tag 是否已存在”部分,当然启用了会给测试CI带来麻烦
PS: 不需要CI的提交只需添加[skip ci]