Releases: machinewrapped/gpt-subtrans
Smarter subtitle batching
This release introduces a new subtitle batcher that tries to divide large scenes up more intelligently by taking gap length into account. This usually results in fewer, larger batches but it can sometimes have the opposite effect - hopefully they're always "better" batches though. The old batcher can be enabled in the New Project dialog to compare the results.
This release also features a better separation between global settings and project options - changing one no longer affects the other, which should lead to fewer surprises.
Additionally, instructions are no longer reloaded automatically from the instruction file for existing projects, they must be loaded or edited manually from the project GPT settings to update them.
Added icon, logo and About dialog
Nothing useful added in this release, but it's a step towards v1.0.0!
Fix for custom project instructions
Fixes:
- Don't reload instructions when reloading project files if they have been modified
- Fix for an error when selecting individual subtitle lines
I've also updated the makedistro-mac script to try to force fetching universal binaries for all the project dependencies so that it works equally well on ARM and Intel CPUs. It seems fine on ARM, but I depend on user feedback regarding Intel macs.
Option to include original text in translation
Plus some minor bug fixes and improvements. Let me know if you spot any new issues.
What's Changed
- Add OpenAI API base URL option to installation script by @eMUQI in #57
- Option to include original text in translated subtitles by @machinewrapped in #59
- MacOS release is now a universal binary
New Contributors
Full Changelog: v0.3.2...v0.3.3
First Run Options fixed and extended
Fixed a bug with the First Run Options dialog, added a couple of extra options, and rewrote it to be more consistent with the other settings dialogs.
Configurable api_base
Option to set a custom API base (thanks to @cddqssc )
Handle failure to retrieve available GPT model list more gracefully.
v0.3.0 GPT4 support + split scenes & batches
This is a semi-major release, integrating a long-forked branch that adds commands to split scenes and batches, which required an overhaul of how the ViewModel is constructed for the GUI. This should improve stability, though there are still some rough edges.
I have also updated the OpenAI library to add support for GPT4, if you have an api_key on a paid plan. Be aware that translating with GPT4 costs approximately ten times as much as using GPT3.5, for only marginally better results (as such, it is not the default).
There is now a settings dialog when starting a new project (by loading an SRT file without one) to set batching parameters, with a preview of the results.
I have also changed the synopsis
argument to description
, to discourage GPT from over-reaching in its from scene and batch summaries.
There are many other nips & tucks to improve usability, particularly for Dark Mode users on a Mac.
UI support for larger batches
A very minor release that increases the maximum value for batch sizes in the GUI, to take advantage of OpenAI's new gpt-3.5-turbo-16k model.
Also, all subtitles are now displayed by default if no scenes or batches are selected, e.g. when a file is first opened.
Bug fixes and default options updated
Minor update with some bug fixes and tweaks:
- Changed translated file suffix to -GPT, since it's not really ChatGPT we're using as a translator, but the base model.
- Increased the default batch size and threshold, since desyncs seem to be much less of a problem now
- Fix for partial matches in project options
- Handle blank subtitles in input file (please try to avoid it anyway)
- Tweaked context summary format and instructions to get better, less imaginative batch & scene summaries
- Use a better default if movie name is not explicitly specified (thanks @AChangAZha)
- Trying normalizing newlines when opening subtitle/project files (speculative fix for a Linux issue)
Project settings and partial word substitutions
Fix for project settings passed on the command line not getting written to the project.
Fix to better support word boundary detection for substitutions in Unicode character sets, and an option to ignore them completely.