Files
ocr_data/requirements.txt
2026-09-28 16:09:31 +08:00

24 lines
954 B
Plaintext
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# 视频字幕提取系统依赖
# 安装: pip install -r requirements.txt
# 另需 PATH 中的外部工具: ffmpeg / ffprobe、coscli(详见 CLAUDE.md)
# 图像与数值处理
opencv-python-headless>=4.8.0 # headless 版无需系统 libGL,适合无界面/离线服务器
numpy>=1.24,<3.0
Pillow>=10.0.0
scikit-learn>=1.3.0 # DBSCAN 水印聚类
# 中文文本处理
jieba>=0.42.1 # 分词
pypinyin>=0.49.0 # 拼音匹配(音频与OCR文本对齐)
zhconv>=1.4.3 # 繁简转换
# 音频与语音识别
pydub>=0.25.1 # 音频切片(依赖 ffmpeg)
av>=11.0,<14.0 # faster-whisper 依赖;钉带预编译wheel的版本,避免本地编译ffmpeg
faster-whisper>=1.0.0 # Whisper 语音识别(int8 量化,CPU/GPU)
# 腾讯云
cos-python-sdk-v5>=1.9.0 # COS 对象存储(import qcloud_cos)
requests>=2.28.0 # 腾讯云 OCR API 调用