- Aug 17, 2016
- 558
- 2,491
I'm just going to be honest, looking at this I'm pretty lost.
I have no idea how someone is supposed to use that.
I have no idea how someone is supposed to use that.
- Aug 17, 2016
- 558
- 2,491
Finally finished a serious offline DSLR test with the new models.
This is only for someone with bad hardware. If you have a high-end rig the tests and conclusion do not apply to you at all.
On a 9 year old PC that was expensive back then, but never received any hardware upgrade.
250000 characters of text, that has a lot of @1 placeholders \n[] commands and \c[] commands.
Test 1
Primary model Qwen3 VL 8B Instruct abliterated v2 I1 (Q5_K_S)
Fallback model Gemma3 27B abliterated dpo I1 (Q4_K_S)
The translation took ~8.5 hours. Not a single complete failure.
Test 2
Primary model Qwen3 VL 4B Instruct abliterated v1 (Q8_0)
Fallback model Qwen3 VL 8B Instruct abliterated v2 (Q8_0)
The translation took ~3.5 hours. 7 cells failed completely and need manual fixing.
Obervations:
Test 1 was a failure on this hardware.
The Primary model actually screwed up a lot constantly requiring the large fallback model to step in which is why it took so long.
8.5 hours for a mediocre translation of a medium sized game is not acceptable.
If you think about the monetary value of the power consumption, wear, and it simply blocking the PC, you could pay deepseek instead and have a faster better translation.
Test 2 was also a failure, although a less bad one.
3.5 hours is still really long considering it had complete failures.
The Primary model actually performed basically the same as the primary in the first test.
The fallback model was too big to offload into the old GPU and as a result pretty slow and did not have a particularly good rate at fixing stuff. Meaning on those 7 complete failures it just wasted a really long time failing.
Current Conclusion:
If you have outdated hardware I would use the biggest abliterated Qwen3 model you can fully fit in your GPU as a primary model and then use DeepSeekV3-0324 as fallback option with the free requests on OpenRouter.
That would be quite fast, free, you would not have a single complete failure, and if the game you are translating has a lot of \c[] commands and stuff like that you will likely still get a significantly better translation than with SugoiV4 based SLR.
If you absolutely want to keep it offline I would honestly just turn the fallback option off and once it finishes manually fix the cells with the TRANSLATIONFAILURE error code (Worst case just run normal SLR on them). That would be so much faster than trying to make a huge model do it for you.
If none of the models fit in your GPU, stick to SLR, it's not worth it.
This is only for someone with bad hardware. If you have a high-end rig the tests and conclusion do not apply to you at all.
On a 9 year old PC that was expensive back then, but never received any hardware upgrade.
250000 characters of text, that has a lot of @1 placeholders \n[] commands and \c[] commands.
Test 1
Primary model Qwen3 VL 8B Instruct abliterated v2 I1 (Q5_K_S)
Fallback model Gemma3 27B abliterated dpo I1 (Q4_K_S)
The translation took ~8.5 hours. Not a single complete failure.
Test 2
Primary model Qwen3 VL 4B Instruct abliterated v1 (Q8_0)
Fallback model Qwen3 VL 8B Instruct abliterated v2 (Q8_0)
The translation took ~3.5 hours. 7 cells failed completely and need manual fixing.
Obervations:
Test 1 was a failure on this hardware.
The Primary model actually screwed up a lot constantly requiring the large fallback model to step in which is why it took so long.
8.5 hours for a mediocre translation of a medium sized game is not acceptable.
If you think about the monetary value of the power consumption, wear, and it simply blocking the PC, you could pay deepseek instead and have a faster better translation.
Test 2 was also a failure, although a less bad one.
3.5 hours is still really long considering it had complete failures.
The Primary model actually performed basically the same as the primary in the first test.
The fallback model was too big to offload into the old GPU and as a result pretty slow and did not have a particularly good rate at fixing stuff. Meaning on those 7 complete failures it just wasted a really long time failing.
Current Conclusion:
If you have outdated hardware I would use the biggest abliterated Qwen3 model you can fully fit in your GPU as a primary model and then use DeepSeekV3-0324 as fallback option with the free requests on OpenRouter.
That would be quite fast, free, you would not have a single complete failure, and if the game you are translating has a lot of \c[] commands and stuff like that you will likely still get a significantly better translation than with SugoiV4 based SLR.
If you absolutely want to keep it offline I would honestly just turn the fallback option off and once it finishes manually fix the cells with the TRANSLATIONFAILURE error code (Worst case just run normal SLR on them). That would be so much faster than trying to make a huge model do it for you.
If none of the models fit in your GPU, stick to SLR, it's not worth it.
- Aug 17, 2016
- 558
- 2,491
I've released v2.030.
Most notable change: frequency_penalty, presence_penalty, stream, and chat_template_kwargs parameter options to DSLR and parameters are optional now.
(If you leave them blank or use 69 if they are a number, then they will not be sent to the endpoint at all.)
Changes since last changelog post:
2.030
Added frequency_penalty, presence_penalty, stream, and chat_template_kwargs options to DSLR.
Added prompt options for fallback model.
Parameters that are set to either be empty or 69 will no longer be sent to the endpoint.
2.029
When talking to the LLM about text commands DSLR will now use the correct capitalization of the original.
Changed DSLR default settings.
Changed DSLR documentation.
Changed DSLR FullBatch max_tokens calculation to be sustantially lower.
Added better error handling for '400 Bad Request' server errors.
2.028
Added more DSLR options for the fallback model. Fixed the existing ones.
Added adjustments to Temperature and Top K parameters during the last attempts.
If a batch would fail completely because even the fallback model ran out of tries, or it's not even enabled, then it will now accept the translation anyway, but add SHISAYE.FAILEDTRANSLATION into it.
Changed default max tokens to 4000.
2.027
Added FallBack LLM options to DSLR.
Removed outdated information from the documentation.
Most notable change: frequency_penalty, presence_penalty, stream, and chat_template_kwargs parameter options to DSLR and parameters are optional now.
(If you leave them blank or use 69 if they are a number, then they will not be sent to the endpoint at all.)
Changes since last changelog post:
2.030
Added frequency_penalty, presence_penalty, stream, and chat_template_kwargs options to DSLR.
Added prompt options for fallback model.
Parameters that are set to either be empty or 69 will no longer be sent to the endpoint.
2.029
When talking to the LLM about text commands DSLR will now use the correct capitalization of the original.
Changed DSLR default settings.
Changed DSLR documentation.
Changed DSLR FullBatch max_tokens calculation to be sustantially lower.
Added better error handling for '400 Bad Request' server errors.
2.028
Added more DSLR options for the fallback model. Fixed the existing ones.
Added adjustments to Temperature and Top K parameters during the last attempts.
If a batch would fail completely because even the fallback model ran out of tries, or it's not even enabled, then it will now accept the translation anyway, but add SHISAYE.FAILEDTRANSLATION into it.
Changed default max tokens to 4000.
2.027
Added FallBack LLM options to DSLR.
Removed outdated information from the documentation.
- Aug 17, 2016
- 558
- 2,491
I've released v2.032.
To further address the weak hardware DSLR problem I've implemented a new option to limit the fallback attempts to 5 single requests.
Meaning instead of retrying the entire batch it will really only use the fallback model for the current failed translation.
That makes using large models with weak hardware much more viable because it will at worst only make 5 relatively quick attempts and not waste 2 hours.
But that new option would be a terrible idea for a fallback model using some kind of free limited requests/tokens, because it will spam small inefficient requests.
It's only a good idea for something unlimited and free. (If you host the model yourself.)
Changes since last changelog post:
2.032
Fixed it not sending the starter of the context prompt in DSLR.
Changed single request retries to 10 instead of 12.
Added new "Limit Fallback to Single Requests" option.
When enabled it will try 5 more times with the fallback model during single requests instead of the fallback model trying the entire batch again.
It will not retry the batch if those 5 attempts fail.
2.031
Implemented the DSLR endpoint parameter option changes for SEP.
Fixed some wrong text.
To further address the weak hardware DSLR problem I've implemented a new option to limit the fallback attempts to 5 single requests.
Meaning instead of retrying the entire batch it will really only use the fallback model for the current failed translation.
That makes using large models with weak hardware much more viable because it will at worst only make 5 relatively quick attempts and not waste 2 hours.
But that new option would be a terrible idea for a fallback model using some kind of free limited requests/tokens, because it will spam small inefficient requests.
It's only a good idea for something unlimited and free. (If you host the model yourself.)
Changes since last changelog post:
2.032
Fixed it not sending the starter of the context prompt in DSLR.
Changed single request retries to 10 instead of 12.
Added new "Limit Fallback to Single Requests" option.
When enabled it will try 5 more times with the fallback model during single requests instead of the fallback model trying the entire batch again.
It will not retry the batch if those 5 attempts fail.
2.031
Implemented the DSLR endpoint parameter option changes for SEP.
Fixed some wrong text.
- Aug 17, 2016
- 558
- 2,491
Some clarification regarding the latest update.
The "Prepare for Batch Translation" button only needs to be pressed once after creating a new project. You do not need to press it again, it wont do anything negative, but nothing positive either.
The new system determines whether or not you ever pressed the button by a small addition to the cache files and will press the button for you if you try to start a batch translation without it.
That means on old projects it will assume that you've never pressed it until it placed the new information, which is a bit annoying, but wont actually do anything negative to your project (but waste your time).
You can turn this whole deal off in the options menu.
Was this really necessary? Apparently so. Some people will rather take the effort of writing a long message shitting on a project, than read some basic instructions.
The "Prepare for Batch Translation" button only needs to be pressed once after creating a new project. You do not need to press it again, it wont do anything negative, but nothing positive either.
The new system determines whether or not you ever pressed the button by a small addition to the cache files and will press the button for you if you try to start a batch translation without it.
That means on old projects it will assume that you've never pressed it until it placed the new information, which is a bit annoying, but wont actually do anything negative to your project (but waste your time).
You can turn this whole deal off in the options menu.
Was this really necessary? Apparently so. Some people will rather take the effort of writing a long message shitting on a project, than read some basic instructions.
- Aug 17, 2016
- 558
- 2,491
I've made a translation for RJ281598 using DeepSeekV3.2EXP as a test because that's weirdly enough currently the cheapest model, but I can't really recommend it.
When it worked it worked good, but in less than 200k characters it shit the bed 6 times and just replied with "A" or "/" when asked for a full batch.
Not a horrible error to get since obviously it wont really bill you a lot of output tokens for that, but DeepSeekV3-0324 never did that.
I did not test the proper 3.2, yet. (Came out today.)
I also never tried 3.1 Terminus, yet. The normal 3.1 is pretty bad.
When it worked it worked good, but in less than 200k characters it shit the bed 6 times and just replied with "A" or "/" when asked for a full batch.
Not a horrible error to get since obviously it wont really bill you a lot of output tokens for that, but DeepSeekV3-0324 never did that.
I did not test the proper 3.2, yet. (Came out today.)
I also never tried 3.1 Terminus, yet. The normal 3.1 is pretty bad.
- Aug 17, 2016
- 558
- 2,491
Finished tests with basically all DeepSeek versions now.
My Impressions are as follows:
DeepSeekV3 - Decent - Not great not terrible.
DeepSeekV3-0324: Good - Follows instructions very well.
DeepSeekV3.1: Bad - Does not follow instructions, constantly screws up
DeepSeekV3.1-Terminus: Good - Basically the same as V3-0324
DeepSeekV3.2-EXP: Bad - Hangs up spamming the same letter quite often
DeepSeekV3.2: Not great - Hangs up less than 3.2EXP, but it still happens
I did not test 3.1-Exacto or 3.2-Special because they are reasoning models with really weird output, that is currently not supported by DSLR.
Translation quality for all of them is pretty bland/sterile and it prefers to take things in a non lewd way, but the tests were done on 0.1 temperature to give it the best chance to follow instructions, so that's not particularly surprising.
TLDR:
I still only really recommend V3-0324, which is also the model I've tested the most, but if you have a better provider for V3.1-Terminus then go with that, since there doesn't seem to be a whole lot of difference.
My Impressions are as follows:
DeepSeekV3 - Decent - Not great not terrible.
DeepSeekV3-0324: Good - Follows instructions very well.
DeepSeekV3.1: Bad - Does not follow instructions, constantly screws up
DeepSeekV3.1-Terminus: Good - Basically the same as V3-0324
DeepSeekV3.2-EXP: Bad - Hangs up spamming the same letter quite often
DeepSeekV3.2: Not great - Hangs up less than 3.2EXP, but it still happens
I did not test 3.1-Exacto or 3.2-Special because they are reasoning models with really weird output, that is currently not supported by DSLR.
Translation quality for all of them is pretty bland/sterile and it prefers to take things in a non lewd way, but the tests were done on 0.1 temperature to give it the best chance to follow instructions, so that's not particularly surprising.
TLDR:
I still only really recommend V3-0324, which is also the model I've tested the most, but if you have a better provider for V3.1-Terminus then go with that, since there doesn't seem to be a whole lot of difference.
yeah, i don't know exaclty how Gemini Nano was placed in Translator++, but with the new chrome versions it works very well for translations, like a Local AI tranlationI'm just going to be honest, looking at this I'm pretty lost.
I have no idea how someone is supposed to use that.
- Aug 17, 2016
- 558
- 2,491
If it's a free addon for T++ I might be able to integrate it, but SLR Translator's UI is based on a really old version of T++ so I doubt it's a simple drop in, and if it's one of the premium addons it's probably riddled with DRM. Dreamsavior really loves DRM in his supposedly GPLv3 licensed project.
For local AI translations I'm currently using Qwen3 VL 32B abliterated v1, and there's also 8B and 4B versions that still work fairly well. (As long as you use Q6 or higher)
I just run them with LM Studio. DSLR can then talk to that like any other openai endpoint.
I couldn't tell you how they actually compare with Gemini Nano though, because I still have basically no data from that thing.
- Aug 17, 2016
- 558
- 2,491
Bad news. Seems like OpenRouter no longer offers free requests to premium models. You can now only get free requests for stuff you could host yourself or is pretty shit.
No DeepSeekV3.X at all anymore either.
As a result OpenRouter is now basically worthless for DSLR, unless you're planning to pay money.
And even that is a bit "meh" because paying a provider directly is probably cheaper, and OpenRouter credits expire after a year, which is a bit bullshit.
No DeepSeekV3.X at all anymore either.
As a result OpenRouter is now basically worthless for DSLR, unless you're planning to pay money.
And even that is a bit "meh" because paying a provider directly is probably cheaper, and OpenRouter credits expire after a year, which is a bit bullshit.
I Actually have tried both Qwen AI with Lm Studio, they didn't translated for me, and tried with Gemini Nano.
A Simple RPGmaker game(without much text), can be in between 2-5 minutes. For a fairly large game, 25-40 minutes, and a huge game, one hour to more.
Gemini Nano was built to run even in a potato of a pc, but when more powerful your pc is, better response this engine has.
I don't know about plugins on your application, but if you want i can try to create a plugin to integrate for you
- Aug 17, 2016
- 558
- 2,491
That's confusing. As far as my tests with "normal" LLMs went, the abliterated versions of qwen3vl are by far the best local models available.
How did you use them and at what quant?
They perform pretty bad if you use a quantization below Q6.
And of course running them on CPU is dreadfully slow, they need to be offloaded to VRAM to have reasonable speed. (But even the 4B versions aren't thaaat bad.)
If you want, give me an example project, I'll translate it with qwen3vl and then you can compare it with your nano results.
If you want to make something, go ahead.
But I'm not entirely sure if it's worth the effort, only do it if you would use it yourself.
Personally I'm translating stuff with DeepSeekV3.1-terminus, but of course that's not free.
It would need to be fed through the SLRtrans wrapper/escaper system or it will screw up scripts.
You can find examples of how that should look like in the www>addons>SLRtrans>lib>TranslationEngine folder.
- Aug 17, 2016
- 558
- 2,491
I've released v2.042
Since looking up the different model variants can be annoying I've added a new bit to the manual that gives specific LM Studio recommendations based on hardware.
Even if you just have a GPU with 4GB VRAM, as long as it's CUDA/VULKAN capable using DSLR you can get significantly better results than SLR. (And it's still free and offline.)
But please don't waste your time if you would have to run the primary model on CPU. It would take so long that you would spend significantly more money on power than it would cost to use DeepSeek instead.
Changelog since last changelog post:
2.042
Changed some cell tagging for VX.
Fixed some DSLR log entries.
Added new section to the manual with model variant recommendations based on hardware.
2.041
Choice box entries with "|" in them will now be tagged yellow.
Fixed some typos.
2.040
Changed handling of MZ plugins in Commonevents to work with damaged or certain non standard code.
2.039
Adjusted descriptions, documentation, and presets to reflect the OpenRouter changes.
2.038
Fixed some wrong DSLR console logs.
Changed the agressive prompts for Full Batch to mention placeholders.
Updated the DSLR entry of the manual.
2.037
Added some new plugins.js tagging.
Added some patterns to add spaces behind variables if they are followed by stuff like "times".
Added new error check to DSLR Full Batch to reject batches if it completely failed to preserve placeholders or commands.
2.036
Added new repetition_penalty parameter option to DSLR and SEP.
Fixed some minor bugs.
Updated some descriptions.
2.035
Fixed bugs related to v2.034.
Changed some log messages.
2.034
Added new (default ON) option to SLRBatch that presses the "Prepare Project for Batch Translation" button when trying to run a batch translation, if the user has never pressed it before on this project.
2.033
TRANSLATIONFAIL error codes will now be removed when pressing the "Fix Cells and Check for Errors" button, instead the cells will be tagged purple.
Fixed it wrongly keeping the fallback model for all single requests of the batch instead of just the failed one.
Since looking up the different model variants can be annoying I've added a new bit to the manual that gives specific LM Studio recommendations based on hardware.
Even if you just have a GPU with 4GB VRAM, as long as it's CUDA/VULKAN capable using DSLR you can get significantly better results than SLR. (And it's still free and offline.)
But please don't waste your time if you would have to run the primary model on CPU. It would take so long that you would spend significantly more money on power than it would cost to use DeepSeek instead.
Changelog since last changelog post:
2.042
Changed some cell tagging for VX.
Fixed some DSLR log entries.
Added new section to the manual with model variant recommendations based on hardware.
2.041
Choice box entries with "|" in them will now be tagged yellow.
Fixed some typos.
2.040
Changed handling of MZ plugins in Commonevents to work with damaged or certain non standard code.
2.039
Adjusted descriptions, documentation, and presets to reflect the OpenRouter changes.
2.038
Fixed some wrong DSLR console logs.
Changed the agressive prompts for Full Batch to mention placeholders.
Updated the DSLR entry of the manual.
2.037
Added some new plugins.js tagging.
Added some patterns to add spaces behind variables if they are followed by stuff like "times".
Added new error check to DSLR Full Batch to reject batches if it completely failed to preserve placeholders or commands.
2.036
Added new repetition_penalty parameter option to DSLR and SEP.
Fixed some minor bugs.
Updated some descriptions.
2.035
Fixed bugs related to v2.034.
Changed some log messages.
2.034
Added new (default ON) option to SLRBatch that presses the "Prepare Project for Batch Translation" button when trying to run a batch translation, if the user has never pressed it before on this project.
2.033
TRANSLATIONFAIL error codes will now be removed when pressing the "Fix Cells and Check for Errors" button, instead the cells will be tagged purple.
Fixed it wrongly keeping the fallback model for all single requests of the batch instead of just the failed one.
- Aug 17, 2016
- 558
- 2,491
I've released v2.045.
Significant changes to DSLR. If you use that, you should definitely update.
Changelog since last changelog post:
2.045
Introduced new "bad translation" purple tags for wrong line count and missing numbers.
Changed Batch size calculation to just be characters again.
DSLR Changes:
Changed Full Batch divider logic.
Changed wrapper so IDSP will no longer cause a sentence to split.
Added option (on by default) to remove all inner IDSP before sending the request to the LLM
Changed Full Batch calculation to never allow more than twice the maximum size even when it produces less than 40 entries.
Changed Full Batch calculation to be a lot less lenient in counting.
During Single requests wrong linecount is now only a reason for a rejection if it's also either significantly more characters or significantly less.
Changed how context is sent to the LLM, it will now also include the original text and not just successful translations.
It will now always send all error context even on the first try.
Changed log messages to be more accurate.
Changed some wrong descriptions.
2.044
Improved D_Text handling for DSLR, added some isolation patterns for DSLR.
2.043
For DSLR changed console log messages to actually show the entire request body including parameters and prompts instead of just the requested text.
Implemented new check for FullBatch that will now reject a batch if it failed to preserve more than 50% of text commands and placeholders. It wil also reject a batch if the LLM added 50% more than the original amount.
Implemented new detection for "response refusal" messages, but only a few variations so far. It will treat them as Server Errors.
Adjusted a bunch of descriptions.
Fixed some typos.
Significant changes to DSLR. If you use that, you should definitely update.
Changelog since last changelog post:
2.045
Introduced new "bad translation" purple tags for wrong line count and missing numbers.
Changed Batch size calculation to just be characters again.
DSLR Changes:
Changed Full Batch divider logic.
Changed wrapper so IDSP will no longer cause a sentence to split.
Added option (on by default) to remove all inner IDSP before sending the request to the LLM
Changed Full Batch calculation to never allow more than twice the maximum size even when it produces less than 40 entries.
Changed Full Batch calculation to be a lot less lenient in counting.
During Single requests wrong linecount is now only a reason for a rejection if it's also either significantly more characters or significantly less.
Changed how context is sent to the LLM, it will now also include the original text and not just successful translations.
It will now always send all error context even on the first try.
Changed log messages to be more accurate.
Changed some wrong descriptions.
2.044
Improved D_Text handling for DSLR, added some isolation patterns for DSLR.
2.043
For DSLR changed console log messages to actually show the entire request body including parameters and prompts instead of just the requested text.
Implemented new check for FullBatch that will now reject a batch if it failed to preserve more than 50% of text commands and placeholders. It wil also reject a batch if the LLM added 50% more than the original amount.
Implemented new detection for "response refusal" messages, but only a few variations so far. It will treat them as Server Errors.
Adjusted a bunch of descriptions.
Fixed some typos.
- Aug 17, 2016
- 558
- 2,491
I've released v2.046.
I've added experimental support for translations other than Japanese to English to DSLR.
Refer to the manual as to how it works.
It's still kinda annoying to setup, and basically not tested, but at least trying to do that no longer outright crashes everything.
I've added experimental support for translations other than Japanese to English to DSLR.
Refer to the manual as to how it works.
It's still kinda annoying to setup, and basically not tested, but at least trying to do that no longer outright crashes everything.
- Aug 17, 2016
- 558
- 2,491
I've released v2.050 v2.051.
Biggest update in a while.
Loads of improvements and new options.
Happy New Year!
Changelog since last changelog post:
2.051
Fixed issues with some v1 endpoints.
Updated manual.
2.048-2050
Fixed placeholder recovery system.
Added v4 api support to SEP, including option to disable thinking.
SEP's api setting will now also automatically add v1/chat/completions/ if there is nothing similar.
Fixed tons of typos.
DSLR:
Added new options to specify how commands and placeholders are sent to the LLM.
Added automations to adjust placeholder mentions in prompts and error handling based on the currently chosen replacements.
Added option to replace all linebreaks with <br> before sending them to the LLM.
Added special automation for using html5 paragraph tags instead of dividers. (In theory, not tested)
The fallback model will now have its own batch calculation and options.
Added new Max Sent Placeholders option to limit batch size based on how many placeholders or commands are already in it.
Changed all prompts.
Adjusted descriptions.
Changed Options menu order.
Fixed \\i[] commands not making it to DSLR.
Fixed some typos.
2.047
Added DSLR support for v4 endpoints including its thinking parameter.
Cleaned up the old SLR code.
2.046
Added Experimental support for translations other than JP>EN.
Added new General Options called Japanese Language Source, and English Target Source.
They will attempt to skip all code parts that either expect the source to be Japanese or the Target to be English, that cannot be changed in the options menu.
Removed the obsolete character counting option.
To actually use DSLR for other translations the user still needs to adjust prompts and wrapper patterns. There is no automation for that.
Changed the sizes of the DSLR option menu entry fields.
Updated the manual and several descriptions to reflect the changes.
Biggest update in a while.
Loads of improvements and new options.
Happy New Year!
Changelog since last changelog post:
2.051
Fixed issues with some v1 endpoints.
Updated manual.
2.048-2050
Fixed placeholder recovery system.
Added v4 api support to SEP, including option to disable thinking.
SEP's api setting will now also automatically add v1/chat/completions/ if there is nothing similar.
Fixed tons of typos.
DSLR:
Added new options to specify how commands and placeholders are sent to the LLM.
Added automations to adjust placeholder mentions in prompts and error handling based on the currently chosen replacements.
Added option to replace all linebreaks with <br> before sending them to the LLM.
Added special automation for using html5 paragraph tags instead of dividers. (In theory, not tested)
The fallback model will now have its own batch calculation and options.
Added new Max Sent Placeholders option to limit batch size based on how many placeholders or commands are already in it.
Changed all prompts.
Adjusted descriptions.
Changed Options menu order.
Fixed \\i[] commands not making it to DSLR.
Fixed some typos.
2.047
Added DSLR support for v4 endpoints including its thinking parameter.
Cleaned up the old SLR code.
2.046
Added Experimental support for translations other than JP>EN.
Added new General Options called Japanese Language Source, and English Target Source.
They will attempt to skip all code parts that either expect the source to be Japanese or the Target to be English, that cannot be changed in the options menu.
Removed the obsolete character counting option.
To actually use DSLR for other translations the user still needs to adjust prompts and wrapper patterns. There is no automation for that.
Changed the sizes of the DSLR option menu entry fields.
Updated the manual and several descriptions to reflect the changes.
Last edited:
- Aug 17, 2016
- 558
- 2,491
I need some opinions.
The Attached txt files are the contents of a Map001 file in original and 6 translation attempts.
Please rank them for me based on translation quality.
I purposely did not make them a single table, because this is not about nitpicking a single translation, but to compare the readability of the entire block.
If you view multiple as of identical quality just rank them the same.
If you view all of them the same, please still post about it.
This is actually really important going forward.
Current Ranking:
6: 22 points
4: 20 points
2: 16 points
3: 7 points
5: 5 points
1: 5 points
The Attached txt files are the contents of a Map001 file in original and 6 translation attempts.
Please rank them for me based on translation quality.
I purposely did not make them a single table, because this is not about nitpicking a single translation, but to compare the readability of the entire block.
If you view multiple as of identical quality just rank them the same.
If you view all of them the same, please still post about it.
This is actually really important going forward.
Current Ranking:
6: 22 points
4: 20 points
2: 16 points
3: 7 points
5: 5 points
1: 5 points
Last edited:
- Aug 17, 2016
- 558
- 2,491
Changelog Post because Changes happened at some point.
2.054
Improved word wrapping logic.
It will no longer consider abbreviation dots as valid spot for a linebreak.
It will no longer cut repeated punctuation in half even if that would increase the length of the sentence above the limit.
Except for dots, which will not always be placed at the end of a sentence.
Full Batch will now give its request 10% more max_tokens than before. (But never more than the specified maximum value in the options.)
2.053
The Fix Cells and Check for Errors button will now remove '' or "" from translations of cells with the tok/ context. (js/plugins/)
Currently the original text wrongly displays that stuff as needing quotes even though it doesn't.
2.052
Fixed function to compare placeholders.
Changed clicking the welcome screen from opening my subscribestar page to opening the manual.
Nobody donates anyway and maybe someone will now actually read the manual.
2.054
Improved word wrapping logic.
It will no longer consider abbreviation dots as valid spot for a linebreak.
It will no longer cut repeated punctuation in half even if that would increase the length of the sentence above the limit.
Except for dots, which will not always be placed at the end of a sentence.
Full Batch will now give its request 10% more max_tokens than before. (But never more than the specified maximum value in the options.)
2.053
The Fix Cells and Check for Errors button will now remove '' or "" from translations of cells with the tok/ context. (js/plugins/)
Currently the original text wrongly displays that stuff as needing quotes even though it doesn't.
2.052
Fixed function to compare placeholders.
Changed clicking the welcome screen from opening my subscribestar page to opening the manual.
Nobody donates anyway and maybe someone will now actually read the manual.
- Aug 17, 2016
- 558
- 2,491
I've released v2.055 v2.056
Changelog:
2.056
Prepare Project for Batch Translation will no longer remove existing purple tags.
Fixed it being too agressive in tagging certain cells red.
Fixed error checking in Fix Cells and Check for Errors wrongly changing cells affected by the placeholder gender option.
Fixed error checking wrongly calling a missing placeholder additional.
Changed purple tag alert to better convey that there's likely not actually anything wrong.
2.055
Added a new option to DSLR to specify the gender of Name Placeholders (\n[1], \n[2], etc.).
For example if \n[1] is a woman and \n[2] is a man you would change the option to
{["1": "female",
"2": "male"}
and then if the original text includes both \n[1] and \n[2] it will accept:
"\n[1] continued to suck \n[2]'s dick."
"\n[1] continued to suck his dick."
"She continued to suck \n[2]'s dick."
"She continued to suck his dick."
It will reject:
"He continued to suck his dick."
"She continued to suck her dick."
"She continued to suck \n[1]'s dick."
"\n[2] continued to suck his dick."
"\n[1] sucked dick."
"\n[2] got their dick sucked."
Only problem is that it would also accept:
"He continued to suck her dick."
"\n[2] continued to suck her dick."
Because it can see both represented.
But that's a LLM issue and of course it could have also given the wrong
"\n[2] continued to suck \n[1]'s dick."
response and there would be no way for the system to know that.
If you leave the new option empty it will do nothing and just handle it the old way of only accepting the exact placeholder.
So if you do not want to allow it to replace placeholders, simply do not use the option.
Adjusted System prompts to fit the new option and fixed some typos.
Changelog:
2.056
Prepare Project for Batch Translation will no longer remove existing purple tags.
Fixed it being too agressive in tagging certain cells red.
Fixed error checking in Fix Cells and Check for Errors wrongly changing cells affected by the placeholder gender option.
Fixed error checking wrongly calling a missing placeholder additional.
Changed purple tag alert to better convey that there's likely not actually anything wrong.
2.055
Added a new option to DSLR to specify the gender of Name Placeholders (\n[1], \n[2], etc.).
For example if \n[1] is a woman and \n[2] is a man you would change the option to
{["1": "female",
"2": "male"}
and then if the original text includes both \n[1] and \n[2] it will accept:
"\n[1] continued to suck \n[2]'s dick."
"\n[1] continued to suck his dick."
"She continued to suck \n[2]'s dick."
"She continued to suck his dick."
It will reject:
"He continued to suck his dick."
"She continued to suck her dick."
"She continued to suck \n[1]'s dick."
"\n[2] continued to suck his dick."
"\n[1] sucked dick."
"\n[2] got their dick sucked."
Only problem is that it would also accept:
"He continued to suck her dick."
"\n[2] continued to suck her dick."
Because it can see both represented.
But that's a LLM issue and of course it could have also given the wrong
"\n[2] continued to suck \n[1]'s dick."
response and there would be no way for the system to know that.
If you leave the new option empty it will do nothing and just handle it the old way of only accepting the exact placeholder.
So if you do not want to allow it to replace placeholders, simply do not use the option.
Adjusted System prompts to fit the new option and fixed some typos.
Last edited:
- Aug 17, 2016
- 558
- 2,491
A reminder to never fix a working system...
A few updates ago I've introduced a helper function to reduce the amount of characters needed for the SLR dictionary system (pre-defined translations).
All it did was reduce the dictionary from 1.2 million characters of code to 800k.
"To make the code more pretty".
And of course I screwed it up and entries with \ in them no longer worked.
I've fixed it in 2.057, but that's just such a stupid reason for a bug... Gawd.
In case you noticed leftover Japanese in some cells (for example the "obtained X gold" message in MV), this was the reason fir it.
A few updates ago I've introduced a helper function to reduce the amount of characters needed for the SLR dictionary system (pre-defined translations).
All it did was reduce the dictionary from 1.2 million characters of code to 800k.
"To make the code more pretty".
And of course I screwed it up and entries with \ in them no longer worked.
I've fixed it in 2.057, but that's just such a stupid reason for a bug... Gawd.
In case you noticed leftover Japanese in some cells (for example the "obtained X gold" message in MV), this was the reason fir it.
- Aug 17, 2016
- 558
- 2,491
I've released v2.060.
Complete overhaul of DSLR, specifically the Full Batch logic.
When using this version you will probably think it's worse.
Batches fail more often, the log will have more error messages.
It will eat more tokens.
But what's actually happening is that I now have introduced proper translation validation for Full Batch, and it no longer just accepts "kinda usable" batches that it then tries to fix in single line checking, but instead it will now actually tell the LLM to get its shit together and send a proper batch.
In reality I have actually significantly improved how the LLM is being sent the Full Batch request and it will fail less often now. It just looks worse because the system no longer accepts failure.
Because what's the point of saving tokens, if the translation is shit.
Changelog since last changelog post:
2.059-2.060
DSLR
Revamped Full batch system entirely.
Changed how translation requests are fed to the LLM.
Full Batch divider logic is no longer customizable in the options menu. (No longer feasible.)
Changed how batches are checked.
Changed retry logic to use prescise custom prompts depending on the checks.
Changed DSLR wrapper to no longer escape color commands at the start or end of lines.
Fixed placeholder checks for single requests.
Will now remove escaped qwuotes from the response if the original did not have any instead of making a correction request for them.
Adjusted prompts.
Adjusted descriptions.
Known issues:
-On low end machines Full Batch validation can lag a bit, but the added translation accuracy seems worth it.
-Full Batch retries can now eat double the input tokens, as a result local models need to be run with significantly more context length than the standard LM Studio setting.
2.058
DSLR:
When the Full batch retry loop fails because of server issues it will no longer attempt single requests.
When a "content_filter" finish reason is detected the translation will immediately be aborted.
2.057
Fixed a bug in a code shortening function that was preventing SLR dictionary entries with \ in them to work.
A reminder to never fix a working system...
Complete overhaul of DSLR, specifically the Full Batch logic.
When using this version you will probably think it's worse.
Batches fail more often, the log will have more error messages.
It will eat more tokens.
But what's actually happening is that I now have introduced proper translation validation for Full Batch, and it no longer just accepts "kinda usable" batches that it then tries to fix in single line checking, but instead it will now actually tell the LLM to get its shit together and send a proper batch.
In reality I have actually significantly improved how the LLM is being sent the Full Batch request and it will fail less often now. It just looks worse because the system no longer accepts failure.
Because what's the point of saving tokens, if the translation is shit.
Changelog since last changelog post:
2.059-2.060
DSLR
Revamped Full batch system entirely.
Changed how translation requests are fed to the LLM.
Full Batch divider logic is no longer customizable in the options menu. (No longer feasible.)
Changed how batches are checked.
Changed retry logic to use prescise custom prompts depending on the checks.
Changed DSLR wrapper to no longer escape color commands at the start or end of lines.
Fixed placeholder checks for single requests.
Will now remove escaped qwuotes from the response if the original did not have any instead of making a correction request for them.
Adjusted prompts.
Adjusted descriptions.
Known issues:
-On low end machines Full Batch validation can lag a bit, but the added translation accuracy seems worth it.
-Full Batch retries can now eat double the input tokens, as a result local models need to be run with significantly more context length than the standard LM Studio setting.
2.058
DSLR:
When the Full batch retry loop fails because of server issues it will no longer attempt single requests.
When a "content_filter" finish reason is detected the translation will immediately be aborted.
2.057
Fixed a bug in a code shortening function that was preventing SLR dictionary entries with \ in them to work.
A reminder to never fix a working system...
- Aug 17, 2016
- 558
- 2,491
Obligatory Changelog Post:
2.066
Fixed (hopefully all) remaining issues with the DSLR wrapper.
Improved bracket preservation.
Adjusted prompts.
2.065
Added support for the Show Popup function of the PSM MV plugin.
Improved word wrapping for speech bubbles.
Fixed SLRContextID related issues with the DSLR wrapper.
2.064
Added support for the "text" function of the OSW MV plugin.
Changed plugin logic to no longer allow IDSPs and instead replace all space types with NBSPs.
2.063
Fixed an error that caused the new automatic correction prompt for leftover Japanese to crash.
2.062
Fixed Save on each batch option not working.
DSLR
Added new elaborate escape system for nameplates so they actually give the LLM proper context who's talking.
Removed break patterns to give more context and work with the new nameplate system.
Updated prompts and error messages.
Known issue: If a dev screwed up and placed 2 nameplates in the same box the system can fail to preserve brackets and formatting and even the post button error checking might not detect it as an isse.
2.061
SEP
It will no longer discard Paddle's output if the LLM used for correction believes there is no text.
DSLR
Fixed a bug that sometimes deduplicated lines before sending them to the LLM making it loose context.
Fixed a bug escaping nameplates using name commands.
2.066
Fixed (hopefully all) remaining issues with the DSLR wrapper.
Improved bracket preservation.
Adjusted prompts.
2.065
Added support for the Show Popup function of the PSM MV plugin.
Improved word wrapping for speech bubbles.
Fixed SLRContextID related issues with the DSLR wrapper.
2.064
Added support for the "text" function of the OSW MV plugin.
Changed plugin logic to no longer allow IDSPs and instead replace all space types with NBSPs.
2.063
Fixed an error that caused the new automatic correction prompt for leftover Japanese to crash.
2.062
Fixed Save on each batch option not working.
DSLR
Added new elaborate escape system for nameplates so they actually give the LLM proper context who's talking.
Removed break patterns to give more context and work with the new nameplate system.
Updated prompts and error messages.
Known issue: If a dev screwed up and placed 2 nameplates in the same box the system can fail to preserve brackets and formatting and even the post button error checking might not detect it as an isse.
2.061
SEP
It will no longer discard Paddle's output if the LLM used for correction believes there is no text.
DSLR
Fixed a bug that sometimes deduplicated lines before sending them to the LLM making it loose context.
Fixed a bug escaping nameplates using name commands.
- Aug 17, 2016
- 558
- 2,491
I've released v2.067.
Obviously it was still broken. Now it totally, definitely, maybe works.
But in my defense stuff gets somewhat convoluted when your patterns are getting longer than the average hentai cock.
This is the start of the placeholder wrapper for nameplates right now:
Obviously it was still broken. Now it totally, definitely, maybe works.
But in my defense stuff gets somewhat convoluted when your patterns are getting longer than the average hentai cock.
This is the start of the placeholder wrapper for nameplates right now:
JavaScript:
'// Start Front',
/^[ ]*\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*\\+nw?<(?=.*?>[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?)/gmi.toString() + ',',
/^[ ]*\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*\\+nw?<(?=.*?>[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?)/gmi.toString() + ',',
/^[ ]*\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*[ ]*\\+nw?<(?=.*?>[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?)/gmi.toString() + ',',
/^[ ]*\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*\\+nw?<(?=.*?>[ ]*[ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?)/gmi.toString() + ',',
/^[ ]*\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*\\+nw?<(?=.*?>[ ]*[ ]*[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?)/gmi.toString() + ',',
/^[ ]*\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*[ ]*\\+nw?<(?=.*?>[ ]*[ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?)/gmi.toString() + ',',
/^[ ]*\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+nw?<(?=.*?>[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?)/gmi.toString() + ',',
/^[ ]*\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+nw?<(?=.*?>[ ]*[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?)/gmi.toString() + ',',
/^[ ]*\\>[ ]*\\+c\[\d+\][ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*(?=(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\+c\[\d+\][ ]*\\<)/gmi.toString() + ',',
/^[ ]*\\>[ ]*\\+c\[\d+\][ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*(?=(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*[ ]*\\<)/gmi.toString() + ',',
/^[ ]*\\>[ ]*[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*(?=(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\+c\[\d+\][ ]*\\<)/gmi.toString() + ',',
/^[ ]*\\>[ ]*\\+c\[\d+\][ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*(?=(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\+c\[\d+\][ ]*\\<)/gmi.toString() + ',',
/^[ ]*\\>[ ]*\\+c\[\d+\][ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*(?=(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*[ ]*\\<)/gmi.toString() + ',',
/^[ ]*\\>[ ]*[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*(?=(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\+c\[\d+\][ ]*\\<)/gmi.toString() + ',',
/^[ ]*\\>[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*(?=(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\<)/gmi.toString() + ',',
/^[ ]*\\>[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*(?=(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\<)/gmi.toString() + ',',
/^[ ]*\\>[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*[ ]*(?=(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\<)/gmi.toString() + ',',
/^[ ]*\\>[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*(?=(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\<)/gmi.toString() + ',',
/^[ ]*\\>[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*(?=(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\<)/gmi.toString() + ',',
/^[ ]*\\>[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*[ ]*(?=(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\<)/gmi.toString() + ',',
/^[ ]*\\>[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*(?=(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\<)/gmi.toString() + ',',
/^[ ]*\\>[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*(?=(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\<)/gmi.toString() + ',',
'// Start Back',
/(?<!SLRContextID.*)(?<=^@1.*?)>[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=^@1.*?)>[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=^@1.*?)>[ ]*[ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=^@1.*?)>[ ]*[ ]*[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=^@1.*?)>[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=^@1.*?)>[ ]*[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=^@1.*?)[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\+c\[\d+\][ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*\\</gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=^@1.*?)[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*\\</gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=^@1.*?)[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\+c\[\d+\][ ]*\\</gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=^@1.*?)[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*[ ]*\\</gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=^@1.*?)[ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*\\</gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=^@1.*?)[ ]*[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*\\</gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=^@1.*?)[ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\</gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=^@1.*?)[ ]*[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\</gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=^@1.*?)[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\</gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=^@1.*?)[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\</gmi.toString() + ',',
'// End Back',
/(?<!SLRContextID.*)(?<=[ ]*\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*\\+nw?<.*?)>[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*\\+nw?<.*?)>[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*[ ]*\\+nw?<.*?)>[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*\\+nw?<.*?)>[ ]*[ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*\\+nw?<.*?)>[ ]*[ ]*[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*[ ]*\\+nw?<.*?)>[ ]*[ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+nw?<.*?)>[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+nw?<.*?)>[ ]*[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\?<?[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\>[ ]*\\+c\[\d+\][ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*)(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\+c\[\d+\][ ]*\\<[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\>[ ]*\\+c\[\d+\][ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*)(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*[ ]*\\<[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\>[ ]*[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*)(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\+c\[\d+\][ ]*\\<[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\>[ ]*\\+c\[\d+\][ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*)(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\+c\[\d+\][ ]*\\<[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\>[ ]*\\+c\[\d+\][ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*)(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*[ ]*\\<[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\>[ ]*[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*)(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\+c\[\d+\][ ]*\\<[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\>[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*)(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\<[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\>[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*)(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\<[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\>[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*[ ]*)(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\<[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\>[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*)(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\<[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\>[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*)(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\<[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\>[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*[ ]*)(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*\\+c\[\d+\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\<[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\>[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*)(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*\\+[FA]+[h]?\[[^\]]+?\][ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\<[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
/(?<!SLRContextID.*)(?<=[ ]*\\>[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*)(?:[Ａ-Ｚａ-ｚ０-９？！＃＄％＆\w一-龠ぁ-ゔァ-ヴー々〆〤ヶﾚﾃﾞｨﾌｧｲｯ ]+|\\nw?\[\d+\]|\\+c\[\d+\])+?[ ]*(?<!\\+c\[\d+)[\]\)}〕〗〙〛\'"""｣〉》」』】）］＞>｝｠"⟩"'`´]*[ ]*\\<[ ]*(?<!SLRContextID)(?= SLRContextID[\s\S]*?SLRContextID$|$)/gmi.toString() + ',',
'// End Front',
/(?<!SLRContextID.*)\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*\\+nw?<(?=.*?@[13][ ]*(?: SLRContextID[\s\S]*?SLRContextID$|$))/gmi.toString() + ',',
/(?<!SLRContextID.*)\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*[ ]*\\+nw?<(?=.*?@[13][ ]*(?: SLRContextID[\s\S]*?SLRContextID$|$))/gmi.toString() + ',',
/(?<!SLRContextID.*)\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*\\+nw?<(?=.*?@[13][ ]*(?: SLRContextID[\s\S]*?SLRContextID$|$))/gmi.toString() + ',',
/(?<!SLRContextID.*)\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*[ ]*\\+nw?<(?=.*?@[13][ ]*(?: SLRContextID[\s\S]*?SLRContextID$|$))/gmi.toString() + ',',
/(?<!SLRContextID.*)\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+nw?<(?=.*?@[13][ ]*(?: SLRContextID[\s\S]*?SLRContextID$|$))/gmi.toString() + ',',
/(?<!SLRContextID.*)\\?>?[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+nw?<(?=.*?@[13][ ]*(?: SLRContextID[\s\S]*?SLRContextID$|$))/gmi.toString() + ',',
/(?<!SLRContextID.*)\\>[ ]*\\+c\[\d+\][ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*(?=.*?@[13][ ]*(?: SLRContextID[\s\S]*?SLRContextID$|$))/gmi.toString() + ',',
/(?<!SLRContextID.*)\\>[ ]*\\+c\[\d+\][ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*[ ]*(?=.*?@[13][ ]*(?: SLRContextID[\s\S]*?SLRContextID$|$))/gmi.toString() + ',',
/(?<!SLRContextID.*)\\>[ ]*[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*(?=.*?@[13][ ]*(?: SLRContextID[\s\S]*?SLRContextID$|$))/gmi.toString() + ',',
/(?<!SLRContextID.*)\\>[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*\\+c\[\d+\][ ]*(?=.*?@[13][ ]*(?: SLRContextID[\s\S]*?SLRContextID$|$))/gmi.toString() + ',',
/(?<!SLRContextID.*)\\>[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*[ ]*(?=.*?@[13][ ]*(?: SLRContextID[\s\S]*?SLRContextID$|$))/gmi.toString() + ',',
/(?<!SLRContextID.*)\\>[ ]*[〔⟨〖〘〚\'"""｢〈《「『【（［\[\({＜<｛｟"'´`"]*[ ]*(?=.*?@[13][ ]*(?: SLRContextID[\s\S]*?SLRContextID$|$))/gmi.toString() + ',',
'// Leftover Modifier',
/(?<!SLRContextID.*)(?<=\\nw?<.*?>[ ]*|\\nw?\[\d+\][ ]*)\\+[FA]+[H]?\[[^\]]+\]/gi.toString() + ',',- Aug 17, 2016
- 558
- 2,491
I've released v2.072 v2.073
Finally fully fixed crashes during the Full batch validation.
Because I had to do several hours of testing anyway I've tested new local models and optimized stuff for them.
You can now successfully use the Full Batch option for models as small as qwen3-4b-instruct-2507-heretic-v4 at Q8_0. (4.3GB increased to ~5GB when used with 12k context length)
That means a reasonably fast and pretty decent translation that can actually use the correct pronouns and is free (if you have 6GB VRAM).
Changelog since last Changelog post:
2.073
The MV and MZ parsers will now collect status "name" entries rarely used for status change text displays.
DSLR
Added support for \NW[\N[1]] type nameplates.
2.072
Made better escaping for \$ commands.
DSLR
Significantly improved Full Batch validation logic.
Fixed evaluation for leftover japanese.
Made retry prompts for missing quotes more effective.
Updated documentation a bit.
2.071
DSLR
Fixed a serious bug that was able to cause catastrophic backtracking during the Full Batch validation step.
Fixed a problem that caused the SLRContextID to not be escaped when a nameplate was added at the end of the dialogue.
Made server error handling more robust.
Optimized the main process of the Full Batch validation significantly. (Should be much faster now, but do the same.)
Added new retry loop skipping validation when the LLM did not actually translate anything.
Changed some default values.
2.070
Fixed some word wrapping bugs.
It will no longer escape potential filenames and instead tag suspected untagged cells yellow.
Added support for the CommonPopup MV plugin.
2.069
SEP
Added options for custom api request headers and non standard parameters.
DSLR
Added options for custom api request headers and non standard parameters and separate ones for the fallback model.
Made robust "fail gracefully" timeout for batch validation if it gets stuck for more than 5 minutes.
Changed default placeholder replacements to eat less tokens.
2.068
Added support for a new version of the GalgeChoiceWindow MZ plugin.
Removed all obsolete or broken translator options.
They still exist in the files if someone absolutely needs them, but I no longer want to "imply support" for them.
DSLR
Fixed a Batch Translation with the LimitedFallback option enabled not continuing after a complete translation failure.
Added a 5 minute timeout to the batch validation system, so that if it gets stuck in a loop it just rejects the batch and the translation continues. (In theory, I've never seen it actually do it.)
2.067
Fix Cells and Check for Errors will now remove unnecessary spaces around monospace brackets.
Fix Cells and Check for Errors will no longer screw up ??? or !!! names.
DSLR
Fixed bracket preservation system still not working correctly with the new nameplate logic.
Fixed wrapper patterns still not covering every possible nameplate speechbubble combination. (toats fr dis tiem)
Finally fully fixed crashes during the Full batch validation.
Because I had to do several hours of testing anyway I've tested new local models and optimized stuff for them.
You can now successfully use the Full Batch option for models as small as qwen3-4b-instruct-2507-heretic-v4 at Q8_0. (4.3GB increased to ~5GB when used with 12k context length)
That means a reasonably fast and pretty decent translation that can actually use the correct pronouns and is free (if you have 6GB VRAM).
Changelog since last Changelog post:
2.073
The MV and MZ parsers will now collect status "name" entries rarely used for status change text displays.
DSLR
Added support for \NW[\N[1]] type nameplates.
2.072
Made better escaping for \$ commands.
DSLR
Significantly improved Full Batch validation logic.
Fixed evaluation for leftover japanese.
Made retry prompts for missing quotes more effective.
Updated documentation a bit.
2.071
DSLR
Fixed a serious bug that was able to cause catastrophic backtracking during the Full Batch validation step.
Fixed a problem that caused the SLRContextID to not be escaped when a nameplate was added at the end of the dialogue.
Made server error handling more robust.
Optimized the main process of the Full Batch validation significantly. (Should be much faster now, but do the same.)
Added new retry loop skipping validation when the LLM did not actually translate anything.
Changed some default values.
2.070
Fixed some word wrapping bugs.
It will no longer escape potential filenames and instead tag suspected untagged cells yellow.
Added support for the CommonPopup MV plugin.
2.069
SEP
Added options for custom api request headers and non standard parameters.
DSLR
Added options for custom api request headers and non standard parameters and separate ones for the fallback model.
Made robust "fail gracefully" timeout for batch validation if it gets stuck for more than 5 minutes.
Changed default placeholder replacements to eat less tokens.
2.068
Added support for a new version of the GalgeChoiceWindow MZ plugin.
Removed all obsolete or broken translator options.
They still exist in the files if someone absolutely needs them, but I no longer want to "imply support" for them.
DSLR
Fixed a Batch Translation with the LimitedFallback option enabled not continuing after a complete translation failure.
Added a 5 minute timeout to the batch validation system, so that if it gets stuck in a loop it just rejects the batch and the translation continues. (In theory, I've never seen it actually do it.)
2.067
Fix Cells and Check for Errors will now remove unnecessary spaces around monospace brackets.
Fix Cells and Check for Errors will no longer screw up ??? or !!! names.
DSLR
Fixed bracket preservation system still not working correctly with the new nameplate logic.
Fixed wrapper patterns still not covering every possible nameplate speechbubble combination. (toats fr dis tiem)
Last edited: