WhisperJAV

meizhong986/WhisperJAV is ranked 1,733 among these 8 peers; nolangz/pixel2motion is ranked 1,731.

WhisperJAV A subtitle generator for Japanese Adult Videos. Free, runs on your own machine, no cloud upload of your media. JAV audio is the opposite of that, and the mismatch breaks them in specific, well-understood ways: 1. *fu*), tricking the model into hearing words where none exist. Add extreme volume swings (whispers to screams) and theatrical role language (*yakuwarigo*) absent from training corpora, and the model's assumptions stop holding. ** These are feature-length recordings, not 30-second clips. This

is a documented failure mode of Whisper-family models [3, 4, 5]. In practice, blanket denoising and vocal isolation can strip the high-frequency detail the model needs to tell consonants apart, making things worse. Fine-tuning on JAV data has its own trap: good datasets are scarce, so fine-tuned models tend to overfit and become hit-or-miss. This is the main defence against hallucination on non-speech. None of this is magic; it is careful plumbing around

known model weaknesses, and the defaults are tuned against ground-truth benchmarks. Results still vary with source audio quality. **Command line:** Any input FFmpeg can read works: MP4, MKV, AVI, WMV, MP3, WAV, FLAC, and so on. Output is SRT (default), WebVTT, or both ( ). 4, upgrade with one command, , because 1. 5 changes no library underneath WhisperJAV. **Saved output folder (GUI):** with *Remember settings* on, an empty saved output folder sent subtitles into WhisperJAV's program folder. **Ollama translations:** repeated and

blocks in a local model's reply are now removed before the reply is read (#455, PR #443). **DeepSeek:** the default model is now . DeepSeek still accepts the old name, (PR #457). **Ensemble defaults:** pass 1 is Qwen3-ASR + FireRedVAD and pass 2 is Anime-Whisper + TEN VAD, both Aggressive. **Colab:** the notebook no longer replaces Colab's PyTorch. It adds the CUDA 12 libraries that faster-whisper needs (#456, #447). **If you run WhisperJAV from scripts:** in a two-pass run

, a pass 1 on Qwen3-ASR or a pass 2 on anime-whisper now defaults to Aggressive with FireRedVAD (pass 1) or TEN (pass 2). A pass 1 on Qwen3-ASR stops before transcribing if FireRedVAD is not installed. 4 **Bug fixes, hardening, and better subtitle timing for ChronosJAV. 4 changes no library underneath WhisperJAV. Full detail, including every change and who reported it: **release notes**. **Subtitles stay in time in films with holes in their audio. ** Some downloaded films

have hidden holes in their audio track. WhisperJAV now fills the holes with silence while extracting the audio, so subtitle times stay in step with the video. Every file is checked as it is extracted. A damaged file is still transcribed, and the run summary lists it as , with the reason. To stop such files instead, use , or tick **Treat 'suspect' files as failures** in the GUI. **An attempt to improve ChronosJAV timing** (#433, #421, #417, #437, #427). For Qwen3

-ASR and anime-whisper, the longest piece of speech sent to the model is now 4 seconds at every sensitivity