mirror of
https://github.com/YaoFANGUK/video-subtitle-remover.git
synced 2026-04-28 20:07:33 +08:00
70e669e9d4
- PaddleOCR 2.10.0 升级至 3.4.0，使用新的 TextDetection API 替代旧版 TextDetector - V5 模型替换为 PaddleX 格式（inference.pdiparams + inference.yml） - 移除 PP-OCRv4 模型（backend/models/V4），仅保留 PP-OCRv5 - 字幕检测选项重命名为"快速"和"精准" - 清理 requirements.txt，移除 11 个未使用的依赖，补充缺失的依赖 - 更新设计素材 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
29 lines
644 B
Plaintext
29 lines
644 B
Plaintext
filesplit==3.0.2
|
|
opencv-python==4.11.0.86
|
|
scikit-image==0.25.2
|
|
tqdm==4.67.1
|
|
pyside6-fluent-widgets==1.7.7
|
|
numpy==2.2.5
|
|
av==17.0.0
|
|
einops==0.8.1
|
|
paddleocr==3.4.0
|
|
matplotlib
|
|
Pillow
|
|
scipy
|
|
requests
|
|
darkdetect
|
|
je-showinfilemanager==1.1.6a4
|
|
# torch and torchvision are installed separately (see Dockerfile for platform-specific versions)
|
|
|
|
# Training only
|
|
#matplotlib
|
|
#lpips
|
|
#tensorboardX
|
|
|
|
# Hardware acceleration
|
|
#onnxruntime-gpu==1.20.1; sys_platform == 'linux'
|
|
|
|
# do not upgrade, windows 10/11 compatable issues, check hardware_acclerator.py:100
|
|
#onnxruntime-directml==1.20.1; sys_platform == 'win32'
|
|
#onnxruntime==1.22.0; sys_platform == 'darwin'
|