首次提交
This commit is contained in:
23
requirements.txt
Normal file
23
requirements.txt
Normal file
@@ -0,0 +1,23 @@
|
||||
# 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
|
||||
Reference in New Issue
Block a user