Choose what should happen to this card.
Turn the current audio track into timed Japanese subtitles. Audio stays on this device.
SubMiner downloads models, not whisper.cpp or FFmpeg. Install them, or set their paths in Settings → Integrations → Japanese Subtitle Generation.
Start with small for a balance of accuracy and CPU time. Larger models need more memory; speed depends on your hardware. Sizes shown are downloads.
This choice lasts for this SubMiner session. Set the default model in Settings.
Use your own model in Settings → Integrations → Japanese Subtitle Generation → Model Path.
Uses a small Silero model to transcribe separate speech passages. May skip songs, quiet speech, and dialogue under music. Requires whisper.cpp's speech detector.
Applies for this session. Set VAD Model Path in Settings to enable it by default.
The generated SRT will be saved locally and loaded into the player. You can close this window while it runs.