Recent content by counter_productive

Let me know I can touch some of them up. My typical workflow is I just touchup subs as I watch them, and sometimes only a scene or two at a time. I lived in Japan for ~10 years and my Japanese is probably Intermediate level.

MESU-103 - Overtime sex with a lady boss and Nakadashi office Yuu Shinoda MESU-105 - Lucky moment with Ayumi Natsukawa, a mature woman who has just joined a three-star soap store and has unlimited ejaculation! MEYD-779 - The big ass and thighs of the brother and sister-in-law are too much of a...

A few DOCP movies which are Memorial Nude (メモリアルヌードフォト) theme DOCP-227 DOCP-235 DOCP-268 DOCP-307 DOCP-364 Transcription: whisper Translation: deepl Little to no edits...

Transcription: whisper Translation: deepl Little to no edits... 348NTR series. Usually short. Entertaining subtitles.

Attached: ADZ-269, FAX-133, IPTD-534, JUFD-182, ONED-590, ONED-939, ONSD-724, ONSD-724, RBD-369, ROE-009, ROE-010, ROE-014, ROE-015, ROE-018, ROE-019, ROE-020, ROE-021, ROE-023, ROE-024, ROE-025, ROE-027, ROE-028, ROE-031, ROE-032, ROE-033, ROE-035, ROE-036, ROE-043, ROE-053, ROE-056, ROE-066...

Used whisper + deepl. machine translated. filtered by using a text file that I store strings to ignore. I've uploaded my ignore file in case others might find it useful to filter their own whisper translations. Contents: lines_to_be_filtered.txt NDRA-002.dual.srt ROE-036.dual.srt...

SDNM-347 身長171cm グラビア活動もこなす奇跡の八頭身美人妻 白河花清 41歳 第5章 まるで恋人のように2人きりで濃厚なザーメンを受け止める恍惚の瞬間 待望の初生中出し First upload to the forum. Whisper.cpp for transcription, deepl for translation. No major editing. I had repeats but I have a python script that does some post-processing to remove some strings.

how are you running it? locally using python on your own GPU? With whisper.cpp? a colab instance? So it's looking for previous tokens for context, and if there is a lot of non-normal dialogue (e.g. sex) then it can throw in a wrench in things. There are a few things to try. 1) try different...

When evaluating models don't worry about looking at the output from several models over a 2 hr movie. Sometimes I'll get repeating lines or music as you said, so I will have to add an offset. If using whisper.cpp you can add an offset using the '-ot' parameter. It's in milliseconds. So if...

so if you don't want to use the command line and are using a colab network you can add a few lines of code to pull the model. they are very large though... https://huggingface.co/docs/hub/models-downloading from huggingface_hub import hf_hub_url, cached_download import joblib REPO_ID =...

So that ffmpeg command you listed is the one they recommend: On a bash shell I just loop through and convert all my mp4s to wavs: for f in *.mp4; do ffmpeg -n -i "$f" -ar 16000 -ac 1 -c:a pcm_s16le "../wav/${f%.mp4}.wav"; done I've also noticed sometimes some models work better than others, so...

So I do something similar I have one list that are just strings to ignore. A lot of 'door closing', 'ghost screaming' or various sounds. I also have a two column file that i use for minor replacements, but yeh the file keeps getting larger and larger. I'll do an initial translation, and look at...

I know this is a little old, but I've been running whisper on an mac M1. I experimented around with the different models and found the medium model to perform slightly better. Though the best translation I've found was from a fine-tuned model on hugging face that was specific for japanese. I'm...