See the v1.7.0 release notes for full details about integrated transcription, the major new feature in 1.7.x.
Transcription improvements
This release features significant improvements to the transcription flow, particularly around the way subtitles are divided/grouped into lines. Using a mix of sources, each provider was assessed and analyzed for weaknesses, resulting in some global and specific improvements.
Each provider uses its most reliable signal for content. Sentences that could be dropped or scrambled by the processing are more reliably complete and correct, and timing is validated and adjusted if necessary to avoid over-long or over-short lines.
Most improved is Qwen Local, which is now also fully compatible with macOS.
Multi-lingual transcriptions are handled more intelligently, with language-aware timing validation. More aggressive timing adjustments can be enabled with a new timing_correction_factor (from 0 to 1).
Other improvements to the handling of line breaks, dialog markers and filler word removal should produce translations that need no further work more of the time.
Transcription provider support
- OpenRouter: MAI Transcribe 2 is current state of the art - fast, accurate, reliable and cheap. This should be your first choice.
- Qwen Local: Runs entirely on your machine, so effectively free. Coverage and quality is good, but timing info is incomplete so some subtitles may be misaligned.
- Gemini Transcribe: Fast and reasonably cheap, but prone to silently dropping large chunks of dialogue.
- OpenAI: Old models, expiring API credits... no good reason to use this unless you have some API credits that need burning.
Transcription-aware instructions
An updated instructions file supersedes the old Whispered instructions, with instructions better tailored to translating subtitles sourced from speech recognition. Selected automatically when opening a translation project from the transcription flow.
Qwen Local transcription is now a fully external installation
qwen_asr is no longer bundled with the package - this reduces the package size greatly, as it pulled in many dependencies that are not necessary if you never use Qwen Local, and avoids issues with packages that are pulled in with less permissive licenses.
The Transcription Settings tab in the Settings dialog will walk you through the install process, which is basically the same as the previous Torch installation with a few more packages to download. If you previously set up an external Torch, just point the setup at its location and the additional packages will be installed there.
Qwen Local transcription on macOS
Torch installation was fixed for macOS, and compatibility issues between qwen-asr and pyside6 were resolved.
Optimised startup time
The initialisation of expensive provider SDK's is now deferred, which drastically reduces start up times. A background task warms the selected default provider once the main window is opened.
Improvements to the settings dialogues prevent freezing when other providers are selected, with background initialization and supported model retrieval.
Miscellaneous fixes and improvements
- Selection fixes: Split Batch is available again when one line is selected, and Translate Selection covers exactly what's selected.
- Merged subtitles no longer disappear from the subtitle view, and undoing a merge restores the lines correctly.
- If the translation provider can't be created , translation stops with an error rather than failing for every scene.
- Subtitle files with duplicate line numbers are renumbered when loaded.
- A rejected project file no longer clears the subtitles that are already loaded.
- Fixed an empty proxy setting for OpenRouter and Requesty.
Main changes
- Fix macOS test failures, quiet test noise, and frozen build Qwen startup by @machinewrapped in #443
- Fix merged subtitle display and undo by @machinewrapped in #442
- Simplify subtitle row mapping by @machinewrapped in #444
- Fall back to best available break point when no balanced one exists by @machinewrapped in #441
- Optimise GUI startup and warm used providers by @machinewrapped in #448
- Fixed torch setup for macos by @machinewrapped in #449
- Optimised opening settings dialog by @machinewrapped in #450
- Make provider failures terminal for a translation run by @machinewrapped in #452
- Transcription line assembly: parts first, speaker-aware merging, timing fixes by @machinewrapped in #451
- Make ProjectSelection reflect the explicit selection, and fix Split Batch by @machinewrapped in #456
- Renumber duplicate subtitle line numbers during load by @machinewrapped in #455
- Transcription: derive lines from the transcript for words-only providers, and fix Muse turns over silence by @machinewrapped in #459
- Fix test logging: real integration counts, quiet renumbering warnings by @machinewrapped in #465
- Add a per-provider timing correction factor for transcribed lines by @machinewrapped in #467
- Make transcription chunk bounds provider settings with per-provider defaults by @machinewrapped in #470
- Send app attribution headers with OpenRouter transcription requests by @machinewrapped in #472
- Cut transcription chunks at short or quiet pauses instead of at the cap by @machinewrapped in #471
Full Changelog: v1.7.0...v1.7.2
Note that v1.7.1 was superseded without becoming an official release.