Princeslayer
Active Member
- Jun 10, 2020
- 875
- 415
- 163
So if we use this( and how do we implement it to those games) those Japanese Rpg games will be automatically translated to English?
- Dec 29, 2017
- 3,473
- 6,183
- 676
Well, there's a little more involvement than just running it, and it can take quite a while to process.
You can find basic usage tutorials for the different modules in the help menu that opens if you press F1 with the tool open.
It's not really meant for the individual person to do for their private translation, but the hope would be that one person goes through the process and then shares the resulting translation patch so no one else has to do it anymore.
The original purpose of the SLR project was to make it easy to replace me with someone else, now it evolved beyond that and could even be useful for someone doing a proper translation, due to all the measures to protect scripts.
- Dec 29, 2017
- 3,473
- 6,183
- 676
On a different topic, if someone has a translation patch, or game pre-patched with one, that was removed from F95, or was never here to begin with, or you find it probable for it to disappear here for whatever reason.
Please post in the anime-sharing thread labelled:
Looking for "lost" translations from F95 and ULMF
It's a sticky in the "Translation Discussions" section.
Ideally (but not required) together with the DLsite code of the game, the game version, and the name of the translator.
(I mean translation patches in general, not just made by me, and not just for rpg maker.)
Please post even if you don't actually have the translation, in order to make people aware of it, in case someone else finds it in their stash.
For obvious reasons, let's not elaborate on the topic here.
Please post in the anime-sharing thread labelled:
Looking for "lost" translations from F95 and ULMF
It's a sticky in the "Translation Discussions" section.
Ideally (but not required) together with the DLsite code of the game, the game version, and the name of the translator.
(I mean translation patches in general, not just made by me, and not just for rpg maker.)
Please post even if you don't actually have the translation, in order to make people aware of it, in case someone else finds it in their stash.
For obvious reasons, let's not elaborate on the topic here.
- May 5, 2017
- 23
- 24
- 59
Hey Shisaye excuse me but could you please translate this game? Even if it's just a simple translation? Thanks.
Thread Game Link
Thread Game Link
- Dec 29, 2017
- 3,473
- 6,183
- 676
Sorry,
https://f95zone.to/threads/shisayes-project-list.91651/post-14398145
But I created SLR Translator specifically to replace me.
It's completely free, and core SLR has pretty low requirements to run, so please don't immediately assume that it wont work for you.
- May 5, 2017
- 23
- 24
- 59
I used the translator yes, it was very good but when I tried this game, it translated correctly but the game always gave some error, but I'll try again with more details. But thanks anyway for answering.
- Dec 29, 2017
- 3,473
- 6,183
- 676
Just some numbers to hopefully make certain questions stop.
Let's say we want to translate a game with 4 million characters of text that needs translation (Including duplicates, 16 SLR batches), which would be a small to medium sized game.
And we use deepseek-chat-v3-0324 with the second fastest provider on OpenRouter Baseten (The technically fastest SambaNova is basically a scam), because we want the translation to finish as fast as possible. (There are significantly cheaper options.)
That would be running costs of $0.77/mt input and $0.77/mt output, + 5.5% tax.
A token is on average 4 characters, and we will not be using cache because it makes AI translations worse.
That means the absolute minimum amount to spend on the translation would be $1,65, assuming an optimistic 110% input / 100% output ratio, and if you assume that you do not ever have to redo any part of it due to bugs, and not a single AI response ever needs correction.
If we would have used GPT4.1 instead ($2/mt input $8/mt output + 5.5% tax).
Then (everything else being the same) that would be an absolute minimum of $10,76.
Or differently put, using GPT would be a 552% cost increase compared to using the second fastest DeepSeek provider.
If you feel like the translation is also 552% better go for it, but please note that dazedanon's translations are not in any way representative of the normal quality of GPT4.1, his stuff is not raw GPT output by any means, people don't give him enough credit.
Edit: I purposely picked an expensive DeepSeek provider to mach/be above the speed of GPT, but as a result it makes it look like I'm just trying to make GPT look bad by being so optimistic about input ratio.
Yes using that provider the gap would be quite a bit smaller if you go with a 200% 100% ratio instead, which might actually be more realistic, but if you don't go for the absolute fastest you can get almost the same speed with GMICloud at $0.28 $0.88, and then GPT really looks like overpriced shit regardless how pessimistic you are with the input ratio.
Let's say we want to translate a game with 4 million characters of text that needs translation (Including duplicates, 16 SLR batches), which would be a small to medium sized game.
And we use deepseek-chat-v3-0324 with the second fastest provider on OpenRouter Baseten (The technically fastest SambaNova is basically a scam), because we want the translation to finish as fast as possible. (There are significantly cheaper options.)
That would be running costs of $0.77/mt input and $0.77/mt output, + 5.5% tax.
A token is on average 4 characters, and we will not be using cache because it makes AI translations worse.
That means the absolute minimum amount to spend on the translation would be $1,65, assuming an optimistic 110% input / 100% output ratio, and if you assume that you do not ever have to redo any part of it due to bugs, and not a single AI response ever needs correction.
If we would have used GPT4.1 instead ($2/mt input $8/mt output + 5.5% tax).
Then (everything else being the same) that would be an absolute minimum of $10,76.
Or differently put, using GPT would be a 552% cost increase compared to using the second fastest DeepSeek provider.
If you feel like the translation is also 552% better go for it, but please note that dazedanon's translations are not in any way representative of the normal quality of GPT4.1, his stuff is not raw GPT output by any means, people don't give him enough credit.
Edit: I purposely picked an expensive DeepSeek provider to mach/be above the speed of GPT, but as a result it makes it look like I'm just trying to make GPT look bad by being so optimistic about input ratio.
Yes using that provider the gap would be quite a bit smaller if you go with a 200% 100% ratio instead, which might actually be more realistic, but if you don't go for the absolute fastest you can get almost the same speed with GMICloud at $0.28 $0.88, and then GPT really looks like overpriced shit regardless how pessimistic you are with the input ratio.
Last edited:
- Dec 29, 2017
- 3,473
- 6,183
- 676
On the topic of how I currently choose translation stuff, and why so much of it is loli stuff if I said in the past that I wont work on that.
Basically to give some general context first, I think anime-sharing is a vastly superior site concerning rules and rule enforcement and I'm pretty tired of F95.
But it's one of those "youtube alternative" problems.
Just because a site is "technically" better for a content provider, doesn't mean there's an audience there, because the average person doesn't provide anything, they just grab what's there and they are very unlikely to take the effort to switch to something else even when they notice censorship. And having an audience, someone to actually interact with the content is the most important thing for a creator, especially if you're not even payed.
That means while pretty much the only reason for someone to switch would be exclusive content, you do not want to make exclusive content for a site with low engagement.
And a-s having low engagement is not just the popularity of F95 it's also the fact that by not censoring content the admin of a-s has pissed off a bunch of companies and governments and the site is being scrubbed from search results.
So I'm working on loli stuff to have exclusives for a-s?
No, because again if exclusives was the goal I would just make everything exclusive regardless if it's banned here or not and no one would use it.
It's just it has gotten a heck of a lot easier to make a translation and there are also a lot more official translations now, which means games allowed here, with a translation request thread here, usually already have a translation or will be officially translated because then they are probably also allowed on steam.
As a result most games that are left without a translation, that are "actually" hopeless, or that I get bug reports for, are games that are banned here and/or banned on steam. (Yes F95 even banned some games available on steam, that's how stupid it has gotten.)
And so even though I'm really not a big fan of loli, and I don't like potential legal implications of loli in the future, they just tend to make the most sense for me to translate if my goal is still to round up hopeless games.
Edit: I should also mention that I stopped including WIP stuff in my list, only finished projects.
Basically to give some general context first, I think anime-sharing is a vastly superior site concerning rules and rule enforcement and I'm pretty tired of F95.
But it's one of those "youtube alternative" problems.
Just because a site is "technically" better for a content provider, doesn't mean there's an audience there, because the average person doesn't provide anything, they just grab what's there and they are very unlikely to take the effort to switch to something else even when they notice censorship. And having an audience, someone to actually interact with the content is the most important thing for a creator, especially if you're not even payed.
That means while pretty much the only reason for someone to switch would be exclusive content, you do not want to make exclusive content for a site with low engagement.
And a-s having low engagement is not just the popularity of F95 it's also the fact that by not censoring content the admin of a-s has pissed off a bunch of companies and governments and the site is being scrubbed from search results.
So I'm working on loli stuff to have exclusives for a-s?
No, because again if exclusives was the goal I would just make everything exclusive regardless if it's banned here or not and no one would use it.
It's just it has gotten a heck of a lot easier to make a translation and there are also a lot more official translations now, which means games allowed here, with a translation request thread here, usually already have a translation or will be officially translated because then they are probably also allowed on steam.
As a result most games that are left without a translation, that are "actually" hopeless, or that I get bug reports for, are games that are banned here and/or banned on steam. (Yes F95 even banned some games available on steam, that's how stupid it has gotten.)
And so even though I'm really not a big fan of loli, and I don't like potential legal implications of loli in the future, they just tend to make the most sense for me to translate if my goal is still to round up hopeless games.
Edit: I should also mention that I stopped including WIP stuff in my list, only finished projects.
Last edited: