Search results

I can't open it. The file has been corrupted or is not a valid notebook file.

Yes both scripts will work. If you are not able to start the script, then you missed installing something. Ask Claude, Gemini, Perplexity or ChatGPT for installation help. Here are some quick instructions from ChatGPT: Check your python version python3 --version To install google chrome: sudo...

Having Python installed on your PC will save you so much time. I have lots of Python scripts to share. I have Python 3.10.11 installed for reference. My clean_japanese.py removes repetitions, cleans up moaning, deletes garbage lines and does replacements of mis-transcribed phrases with whatever...

Keep the audio file, json and partial filenames the same and it will load the partial srt tomorrow and continue appending to it. Or upload those files to a different Colab account and it will also continue.

Yup, the initial_prompt tells Whisper to transcribe everything even moans. You don't have to manually clean it. Use my clean_japanese.py. It will automatically clean all repetitions, moaning, laughing, and garbage.

Before it can only process one file then it will say out of memory error. Now it'll keep continuing after each file without out of memory errors.

I reuploaded it. See my edit.

Yes, all results are saved in the partial.srt and ckpt.json found inside /WhisperJAV. Don't move or edit those files as it's running.

I added checkpoint resume functionality to Mei2's WhisperWithVAD_pro Colab code. Download it in the Tutorials Whisper thread. I updated my clean_japanese.py. A lot more patterns have been added. It's very comprehensive now. I updated the SYS_MSG in my deepseek_srt.py. Now the translations have...

Gemini Pro helped me add checkpoint resume functionality to Mei2's WhisperWithVAD_pro Colab code. Now it saves a checkpoint file and partial srt periodically. Ever been frustrated when you reached the time limit and all progress is lost? If you crash from memory issues, reach the time limit...

I wanted to grab the Chinese subtitle for MFYD-001 but it never got made. Time to revisit Whisper. I didn't know about the PRO version until recently. Mei2 is awesome for making it. I wanted to improve my workflow and so I made a Python script for cleaning the Japanese srt. Garbage lines of...

With an extra step of restart session, you can avoid the "numpy.dtype size changed" error without needing to upgrade those packages. The workflow is mount Google Drive, setup, click runtime>restart session, set parameters, then run Whisper. In WhisperPro, I use an initial_prompt =...

Just learned about this. Use the new model for improved translations. Change from MODEL = "accounts/fireworks/models/deepseek-v3" to MODEL = "accounts/fireworks/models/deepseek-v3-0324". My first run caused line merges at TEMPERATURE = 0.9. My new recommended default is TEMPERATURE = 0.8 Nao...

It's been a long time since I posted. I recently discovered how good Deepseek is, and I got excited. I spent ~30 hours on this Python Script to translate Chinese SRT files to English using Deepseek v3. Why use it? My Python script translates in batches, so it has the context of previous lines...

Whisper subs. I deleted a lot of hallucinations and garbage sentences, but I didn't change any pronouns. I updated the garbage list and hallucination suppression in google colab. https://drive.google.com/file/d/19oycJYPsBzwzaOUebkGVH80tty2n5KG6/view?usp=share_link. Feel free to make a copy to...

I don't see VAD (Voice Activity Detection) in that version. It was a hassle to install https://colab.research.google.com/github/ANonEntity/WhisperWithVAD/blob/main/WhisperWithVAD.ipynb locally but it was worth it. There were so many things to install like CUDA, cudnn, (I think these two are...

I also arrived at the same conclusions. After extensive testing, I've settled on 3.2 chunk_threshold and 0.3 vad_threshold for a good balance between catching short sentences and natural sounding speech. Source separation also fails to work. The spleeter package is to blame. I also use...

https://easypronunciation.com/en/merge-two-subtitle-files-online

With subs like that, use mpv player to sync them on the fly. As the video progresses and gets out of sync, I pause, then press ctrl shift left which cycles through to the previous dialogue. I don't know any other video players with this feature.

Thanks to the poster from javbus forum for updating it. Reuploaded 31000外挂字幕 https://www119.zippyshare.com/v/ccf2Ic8n/file.html zip password: www.javbus.com

There's a 29000+ Chinese subs posted on javbus forums on 2021-9-8. I reuploaded to zippyshare https://www49.zippyshare.com/v/310HZhjm/file.html Rar password: www.javbus.com Posting 7 recent Chinese subs (jul, meyd, nsfs, roe, ssis, vec) and ran it through DeepL translate.

I have an atid-467 with triple the number of lines. I can tell that most of the above subs are made with autosub or pytranscriber. Posting 9 subs translated from Chinese on DeepL: atid-467,jul-633,jul-635,jul-645,mide-944,mide-947,sprd-1422,sprd-1425,waaa-077

Nice guide. Do you have a recommended image viewer to delete blanks? It's kinda tedious to manually delete blanks. I was thinking you can click Create TXTImages which automatically detects blanks. Then you can run a script to compare to see if the RGBImage filename is in the same list as...

Got some of the recent JUL and SPRD subtitles for anyone who likes milfs. jul-540, jul-546, jul-554, sprd-1396, sprd-1397, sprd-1398, sprd-1399. All translated by Deepl with no editing. Not sure if it's mentioned but the software Everything by voidtools changed my life. It's so much faster than...

GVG-721 Mother Adolescent - Reiko Kobayakawa (OCR'd from Spanish) JUL-377 Married Woman Secretary - Marina Shiraishi

HK singer Ivana Wong has the same ears that stick out like Mori Hotaru

vec-393, meyd-203, meyd-220, meyd-222, miad-732, scpx-262, sw-332, meyd-043, meyd-122, meyd-138, iene-711, mdyd-988, meyd-039

Btw, daily 3 money can only be redeemed on mobile devices. Instructions: login to website > click the last tab for your profile > red circle with check mark 每日签到 > red rectangle.

VENU-549 Mother And Son Of Affection Starting From Kiss, Intimacy, Intense Sex - Murakami Ryoko VEC-266 Cheating Wife Invites A Hot Stud Over While Her Husband's Away For 3 Whole Days Of Tender Loving: They Kiss, They Caress, And They Fuck Over And Over - Naho Hazuki

I already invited ~6 people and I'm low on gold. Maybe ask George1967? He has surpassed everyone's gold amount with his unique skill of posting decensored videos. Edit: It's a bad idea to join because currently daily login 3 money is cancelled. So unless you can post subtitles, you have no way...

The timeline was messed up so I scanned the subtitled video from sehuatang, then took that timeline and auto translated on Deepl.

I spent 3 days on my Python script that uses Selenium to automate Chinese srt to English on Deepl website. The hardest challenge was figuring out how to split the text file into chunks because of the 5000 character limit. Automatically translate a folder of srt files without even moving your...

VENU-448 Love Of Mother And Son Beginning With Kiss, Adhesion, Thick Sex Ai Uehara I recorded a 3 min OCR guide. Why overlay text at the top left? Overlay a text that is highly unlikely to appear. It's a technique to identify blank and double lines after using regular expressions. I wrote...

Thanks to javr for extracting GVG-367. He got rewarded his rare movie. I translated it with yandex and google. Then made corrections. There's a 7 gb 1080p torrent on sukebei nyaa or a1080hd Kaori's husband is not having sex anymore. Always too tired and blames it on work. Kaori bought new...

Yesterday I extracted JUFE-130 from a japonx video. I use VSF and Baidu ocr. I breezed through the proofreading since there were many perfect lines, <1.5 hours. Honestly translating and manually correcting lines takes longer. I don't always feel like translating... JUFE-130 is aunt and nephew...

Using Ansi 32 bit version? Did you put those files in the folder \VideoSubFinder_4.30_x64\Release_x64? Did you input your api key and secret? Do you have TXTImages? Double click the script. Press ctrl+f9 to start. You should see txt files getting created one by one in TXTResults.

Follow this guide. The author wrote a script in autohotkey. https://www.sdfert.space/thread-223392-1-2.html

High effort translation. Spent 30 mins translating each one. First I separate the Chinese text, copy paste into Yandex, combine for English srt. Then open both Chinese and English srt side by side. I look at important dialogue and make them more accurate and less robotic. If you want the Chinese...

Baidu is slow for me too, 150KB/s usually. I'll download it too and upload to google drive. Since I'm also keeping your movie, you can have an additional movie from my collection. I only have a few since I spend my gold on subtitles. Sourced from javpapa. I learned how to use Baidu's ocr api...

Enjoy these subs. I simply translated them with Yandex. I don't take ocr credit here.

I'll give you an incentive to extract subtitles. Every two Chinese subtitles that you extract that's never been uploaded anywhere else, will get you one movie in original 6000kbps no watermark. I know Chinese users that practically have every movie not kidding. I'll be the middleman uploading...

Why would traditional translate any differently than simplified? That makes no sense. Traditional has the same meaning as simplified, just visually the characters have more strokes. No idea what you're talking about.

No big deal. I'll assume machine error but didn't bother to check it over. It's fine since it was your only outlier. Hunta-660 is the longest one I've extracted so far. Almost 4 hours long and 1572 lines. If you want to know what videos have hardcoded subtitles, check javpapa.

Arny, why is your hnd-716 translation so terrible? You know zero Chinese but that's no excuse. Look at lines 7-12. Are you replacing every line with "yeah" on purpose? How exactly are you translating them? My Chinese is good yet I just machine translated with no corrections and it's way better...

I'll do it but part 1 is missing and what color are the subtitles? Nevermind. Can't do it. Chinese subs don't exist.

Mostly torrents and Chinese forums. Javlibrary's comment section has many links but most require premium. I did find a couple of users that upload to google drive and mega.

I found mywife.cc Anyone know PRDB website?

I extracted this. It's not bad at all if you can read at least some Chinese characters. Lots of shortcuts like 对不起 (sorry), type dbq instead of dui bu qi, 不行了 = bxl instead of bu xing le. When I get stuck, use a translate app to scan my monitor or handwrite. Use an app that can sync your phone...

I've tons of success. Let me know if you have any OCR request. I can do it pretty fast.