Search results

I found using deepseek through subtitle edit really bad, it was really slow as well. I've never ran deepseek locally tho. I rather use the full big model. There's a couple of sites that have been linked before where people do their translations. There's also a good script that has been linked...

Did he/she finally allow JAV ? I got banned 2 times from that one when it was still new for explicit content. Kinda weird he/she was looking into what you were uploading. It was clearly a manual ban, not some automatic trigger.

This seems to work, it's running right now. It's tight for me the VRAM usage with only 6GB. My latest gfx is AMD so :(, I have to run it on an older machine with a 1660 super. Last time it was weird cause torch.cuda.is_available() returned a false for me when I installed your requirements even...

For me it seems to be using the CPU. I have high CPU load and I see it using only 400MB of VRAM when I start it (It's usually between 3 to 4,5GB). 3% took 10 minutes which is even slow to be CPU. Copyright (c) 2005-2025 NVIDIA Corporation Built on Fri_Feb_21_20:42:46_Pacific_Standard_Time_2025...

Glad you liked it, I'm also incorporating a 2-pass system where we first do a little bit of context extraction to help out the whole translation process. It helps a lot with keeping certain terms and names the same. Example : In the first 600 lines the term 女将 (Okami) could be translated as...

https://github.com/yt-dlp/yt-dlp You gotta work with command line tho, and if it's embedded video you'll first need something that can catch the HLS streams (browser extension), cause just posting URL won't work into the command line. Supports multi-threading downloads as well. Most streaming...

I've switched to your script since the token usage is so much lower. Was using gptsubtitler but the token usage is like 5-6x. I did a few translations wasn't fully happy with the result, so I copied a lot of the prompt stuff gptsubtitler uses. I liked the result a lot more, but it might be a...

https://www.akiba-online.com/threads/post-your-jav-subtitle-files-here-jav-subtitle-repository-jsp-not-a-sub-request-thread.1466451/page-364#post-4904110 This cleaner removes stuff like that, as most hallucinations are always the same (like subscribe to my channel). It's the best one I've seen...

I did some testing with the flash and pro 2.5 model, 2 or 3 months ago, which in the AI universe is a century ago. It was a lil worse imo. The flash version is really cheap and very fast, which imo is really an option if you don't mind the slightly worse translation. Apparently the gemini pro...

Not sure if it's worth it, I think it's more when there's heavy background noise, like music (or a shower). But I am interested if anyone actually has tried it. The re-aligning of timings seems useful tho.

mdx_kim2 could help with that, it's a better voice extraction method than what faster-whisper uses (which is HT demucs I think ?). I use whisperXXL

If all your filenames are like this that's a pretty easy regex "[a-zA-Z]{3,6}-\d{3,4}" Regex is how you deal with stuff like this, if there's different formats you just set up fallbacks. I have a big script that does my filenames but I doubt it will help you much.

Bit of an old post, but I'll give my input If a model starts hallucinating a lot, it's just random. I find it happens like once every 50-100 transcriptions. Redo the transcription and you'll find that suddenly those are gone. Coincidentally I had it happen today as well, it hallucinated like...

Thx for reporting! I had caught this specific problem already. It's all done with a script so some things will get through. This specific problem was because the source files were named like hhd800.com@hmn00451.srt and went through my regex and so got named HMN-004vXX If I remember correctly...

Isn't the solution simple ? Just have duplicates and have them be in both actress folders. I have done it as well with the 25k chinese subtitles I've posted. It gets a bit more complicated when you realize there's so many aliases as well. ex. not everyone will know Lemon Tanaka is actually Karen...

If this ever happens again, I wrote (*cough* claude.ai) a script that detects this and corrects it. Didn't even take 10 minutes, seems to work fine when I converted it to mono and listened to it manually. Just skipped through it tho, so it's not 100% tested Edit : don't use the --plot...

worked great, thx ! I tried the python clean up subs thing, seems a bit aggressive on some things ? I might remove some stuff myself. So i wanted to compare the anime model version vs V2, but I only translated 100 lines and only compared the first 60. I need sleep and can barely keep my eyes...

Wow, that looks really great from a quick glance, but I can't compare this to my own as I don't know how to fix the audio problem. I'd like to see it with actresses that sometimes talk in a very cutesy way, I'm sure any model trained on anime is able to deal with that much more. Ichika...

There's a lot of dialogue in the first half hour, you have 3 lines in the first half hour. The file is only 10kb as well, I got 18kb worth of text out of it. It's how I immediately noticed something was off as well. I've downloaded the 4k version just now, see if anything changes but I doubt...

Yep, I've tried to re-encode it as well, to no avail. It's very weird

I've done some tests as well and V2 is just better from the tests I've done. While there were a few tests where V3 was better, in general V2 was the clear winner for me. From what I've read is that V3 is only better if the audio is super clear, like a podcast. In JAV the audio level quality can...

I do most my translations with gptsubtitler.com and with deepseek. Gptsubtitler is a great tool. Deepseek still has the problem of being really slow during peak times, they offer a discount during non-peak times. The first hour of that is still slow but after that it's fine. Deepseek also...

Little update to the Chinese subtitle pack with about 350 extra subtitles, most of them new of the last 2-3 months. https://pixeldrain.com/u/9n7WpG5w https://pixeldrain.com/u/gPmJQrh6 (a list of all subtitles different from v2 of the pack) Now a full new pack, instead of ordering them by studio...

I've updated the pack. I forgot to extract about 332 .ass files that I missed. Also the python script I put in the first pack is an old one I think, newer version in the new pack as well if someone wants to use it. This is the full pack + update + new python script...

I've cleaned up up some some of the Chinese subtitles packs that were posted here, most were from before 2021-2022 I think. I've added tons of new subtitles from after 2021-2022 that I've found in the RUNBKK packs and scraped a few sites for all their subs. Combined it was probably more than...

This project seems quite abandoned. If you check its GitHub there's a few people mentioning timestamps aren't working, but there's no response.

ooh that makes a lot of sense. I did notice there was a lot of quality difference in between. Sadly I was never able to find out about this Red catalog early enough. Missed out, huh ? :terharu:

Imo they're good enough, and the highest quality out there from all the popular streaming sites. But I do question sometimes some translations as well yeah, pretty sure the person does not speak Japanse either and I wonder what the source of his translations are? Is it just your default subs you...

I gave it a try on a small sample, and it's only seeing 1 speaker while there should be 3. I even configured a number of speakers to 3 and upped the sensitivity and still only saw 1 speaker. Tried it 3 times and 1 time it saw 2. I'll give it another go on Linux in SWL so I can use ROCm, cause...

I wasn't talking about doing a second pass with deepseek, just doing "one pass" twice and getting different results. Dunno if you are writing your own code, but with subtitle edit the response time seems incredibly slow yeah, not sure what's going on. I've been now using GPTSubtitler.com (you...

SONE-604 I Was Left In The Care Of My Uncle As A Teenager, And While I Felt Disgusted, He Licked My Body And Screwed Me. I was using DeepL cause it was mostly free, but I'm now using deepseek which feels so much better. It's so much cheaper than other models, specially now they they are doing...