feat: implement vertical crop, local LLM deepseek-v4-flash, multi-threading, word-level pink box highlight subtitles, and Nextcloud scan sync
This commit is contained in:
@@ -0,0 +1,10 @@
|
||||
-r requirements.txt
|
||||
|
||||
# Optional dependencies for --mode local.
|
||||
yt-dlp>=2024.1.1
|
||||
faster-whisper>=1.0.0
|
||||
openai>=1.0.0
|
||||
google-genai>=1.0.0
|
||||
opencv-python>=4.8.0
|
||||
# torch is only needed if you want CUDA Whisper. CPU works without it.
|
||||
# torch>=2.0
|
||||
Reference in New Issue
Block a user