summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAge
...
| * fix: set gpu device index in whisper modeljsopn2023-06-30
|/
* Fix race condition around audio frames droppingyum2023-06-28
| | | | | | | | | | | onAudioFramesAvailable would bail out if audio_state.audio_paused is set, preventing frames from being dropped. This would cause transcriptions to get repeated sometimes. Now that frame dropping code always runs. Also adjust the code structure of the keyboard/VR input handlers to be more similar.
* Bugfix: commit no longer wipes out audio bufferyum2023-06-28
| | | | | | | | | | | | Audio data is stored in chunks of frames, not in individual frames. When I commit a transcript, I want to get rid of the portion of the audio data responsible for that particular transcript. I have code that does this, but it was dropping a slice of the list assuming that each sample is stored individually. Extra fun: Because we have to decimate mic frames, we have to convert between whisper frames and mic frames to drop the correct amount of audio data.
* Add profanity filteryum2023-06-28
| | | | | | | Add toggle to UI to enable a profanity filter. It replaces vowels in bad words with asterisks. Bugfix: filters now apply to OBS
* Add toggle for debug modeyum2023-06-28
| | | | | | | | Most transcription output is now gone by default. Users can enable a more verbose output by toggling `Enable debug mode`. Bugfix: Toggling off transcription would reset audio state, frequently resulting in the loss of the last few words spoken.
* Add UI for fuzzy commit thresholdyum2023-06-27
| | | | | | | | | | | | | | Recap: In the STT there's an algorithm that tries to determine when a transcript is "stable" enough to commit. If that is too loose, then accuracy suffers; if too strict, then the audio buffer eventually fills. To mitigate the problem, I check whether the last N transcripts are within some edit distance (Levenshtein edit distance) of each other. The fuzzy matching lets us forgive small instabilities, like differences in uppercase/lowercase or punctuation, while rejecting large instabilities. The default value of 8 seems to be in the sweet spot of accuracy & performance, but it will likely be tuned in the future.
* Adjust commit logic to use fuzzy string match thresholdyum2023-06-27
| | | | | | | | ... instead of simple equality. TODO: add UI for threshold. Bugfix: Frame::onAppStop() joins the OBS app thread.
* Add ability to preserve transcript while using push to talkyum2023-06-27
| | | | | | | | | | | | | This is useful when streaming. Occasionally the STT can get into a bad state, and manually segmenting clears it up. However doing so would clear your accumulated transcript, which isn't always desired. Add ability to preserve the transcript. A small wrinkle: the new commit logic requires N consecutive identical windows before committing. To make this feature play nicely with it, I had to forcibly commit any preview text that hasn't yet been committed. Failing to do this would usually cause short utterances / the most recently said stuff to get wiped out.
* Add grey background to browser srcyum2023-06-27
| | | | | | Should improve legibility. * Update README
* Limit priority of transcription processyum2023-06-27
| | | | Seems to help reduce impact on time-sensitive apps like OBS.
* Scrub out old C++-based Whisper codeyum2023-06-26
| | | | No longer used.
* Add UI for browser srcyum2023-06-26
| | | | Add ability to toggle on/off browser src & configure port.
* Bugfix: Transcript no longer repeats when paused in desktopyum2023-06-26
| | | | | Hitting the desktop keybinding to stop transcription would sometimes cause the last transcript to repeeat itself.
* Add browser source, hardcoded to port 8097yum2023-06-26
| | | | | | | | | | | | | | | | | | | Transcription output now streams to localhost:8097. In OBS: * Create a browser source. * url: localhost:8097 * width: 2200 * height: 400 TODO: * Put behind toggle. * Create input field for port. Misc cleanup: * transcribe.py: Drop frames from audio capture thread instead of the transcription thread. Doing it the other way would result in occasional data loss.
* Remove window duration fieldyum2023-06-24
| | | | | | | | No longer needed with new commit logic (8d0add86f66db532). Assign it to 5 minutes. Assuming 4 bytes per sample @ 16 kHz, this buffer maxes out at 19.2 megabytes of memory usage.
* Remove time-based venv setupyum2023-06-24
| | | | | | | This was slowing down app startup to an unacceptable degree. Now it just runs once ever. Add a button to the debug panel to manually re-setup venv if needed.
* Rework transcription commit logicyum2023-06-24
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | At the core of the STT, there's a loop which uses Whisper to convert audio into a transcript. As you say something, whisper sees growing fragments of your sentence: t0: "Hell" t1: "Hello" t2: "Hello, world!" So we need some algorithm which takes these fragments and accumulates them into an ever-growing transcript. Previously I did this with fuzzy string matching. I'd find the region where the two transcripts overlap and edit the two together to produce a longer transcript. The big problem is that if there's no overlap, it's not clear whether whisper radically changed its mind as to what was said, or whether the user paused for a long time before saying something new. So I'd have to reset the growing transcript. Now I get the timestamps from Whisper and wait for it to give me the same 3 transcripts for the last utterance. Once the transcript stabilizes like this, I commit the text. This enables a temporally stable, ever-growing transcript that's also quite accurate. To prevent a latency regression, I also introduce the notion of "preview text", which is a preview of an utterance that has not yet stabilized. These previews do not contribute to the ever-growing transcript, but do get fed through the rest of the app, so they show up in-game / in OBS. Once they eventually stabilize, they get committed to the ever-growing transcript. This change is lightly tested!
* Begin work integrating pyopenxryum2023-06-19
| | | | | | | | | pyopenvr is deprecated and is causing a user issue (https://github.com/yum-food/TaSTT/issues/2). That user was kind enough to experiment with different configs and didn't find a simple fix. So let's close this tech debt issue the right way.
* Finish translation for Western European language speakersv0.12.0yum2023-05-30
| | | | | | | | | | | | | | NLLB needs its input to be split up into sentences. I use the sentence_splitter Python package to do this. It supports ~20 Western European languages, but notably, no Asian languages. * Sort spoken language list. English is still at the top. * Remove 'Translation source' dropdown. Infer this from the spoken language. * Add lang_compat.py to map language codes between the various libraries (whisper, nllb, sentence_splitter). * Fix bug where old text would appear in textbox when you first bring it up.
* Add ability to translate into 200 languagesyum2023-05-25
| | | | | | | | | Use Meta's No Language Left Behind (NLLB) algorithm to provide translation capabilities into 200 languages. Obviously most are very untested. This requires either 4.1 or 7.1 GB of RAM and significiantly increases transcription latency.
* Add more text filtersyum2023-05-24
| | | | | | | | | | Add 3 filters: * Remove trailing period * Convert to uppercase * Convert to lowercase All may be composed. Upper/lower just overwrite each other so just use one.
* All transcription panel fields now persist across app restartyum2023-05-24
| | | | | | | | | | I forgor to put them into ApplyConfigToInputFields. The reason this is necessary: we need to create the text field where we log things before we can deserialize the config. To keep the code structure "clean" I just wrote another function to apply the config (ApplyConfigToInputFields). However I have to remember to update it when I add new fields.
* Add UI toggle for uwu filteryum2023-05-24
| | | | | UI now has a checkbox for the uwu filter. Does not materially affect resource usage or latency when enabled.
* Begin work on uwu filteryum2023-05-24
| | | | | | Use UwwwuPP to translate your boring old speech into uwu-ified version. Still need to add a UI toggle for this.
* Add ability to type using STTyum2023-05-23
| | | | | | | | | | To use it, do a medium hold + long hold. Keep the long hold depressed until you're done speaking. The transcription will be typed into the currently selected input field. * Add more audio feedback * Make audio feedback play asynchronously so it doesn't slow down the controller input state machine as much.
* Automatically set up virtual envyum2023-05-23
| | | | | | | | | Remove the button. This is a big source of confusion for new users. Now it happens automatically upon starting any task that needs it. * Begin removing CPP implementation of Whisper. faster-whisper is a much easier/better solution. * Flip default of `clear OSC configs` from false to true.
* Add ability to update textbox in placeyum2023-05-22
| | | | | | | By holding the button while talking for at least 1.5 seconds, you can update the contents of the textbox without unlocking it from worldspace. So now you can carefully position your textbox once, then continually speak into it without having to reposition it every time.
* Shader improvementsyum2023-05-22
| | | | | | | * Fix thin outline in transparent region of rounded corners * Remove anti-aliasing. Now that VRC supports it natively, this is no longer necessary. * Use more efficient noise function for dithering.
* Restore mipmap sampling in custom chatboxyum2023-05-22
|
* Add keyboard togglev0.11.4yum2023-05-22
| | | | | | Users can now configure a keybind to start/stop/dismiss the STT when in desktop mode. The default keybind is ctrl+x, since by default VRC doesn't use 'x' for anything.
* Merge pull request #1 from faker2048/patch-1yum-food2023-05-22
|\ | | | | Fix accidental semicolon typo
| * Fix accidental semicolon typofaker2023-05-22
|/
* Enable selecting specific GPU when transcribingyum2023-05-21
| | | | | | Useful on devices with multiple GPUs, such as gaming laptops. * Update GUI/README.md.
* Fix noop animations on current creator companion buildv0.11.3yum2023-05-09
| | | | | | See comment for details. * Update README
* Drop torch from requirements.txtv0.11.2yum2023-05-01
| | | | | | | | | faster-whisper doesn't need it. This reduces install size from 6.00GB with base.en model to 1.70GB. * Use a single sampler in shader (enables using more than 16 textures) * Minor legibility regression - need to improve AA. * Enable backface culling in shader (minor performance win)
* Restore string matching, remove affinity maskv0.11.1yum2023-04-25
| | | | | | Affinity mask no longer affects performance. String matching is still needed for temporal stability in fast-paced long-form transcription tasks.
* Fix custom chatbox zwrite/depthyum2023-04-25
| | | | | | | Depth was being calculated wrong, causing text box to render behind objects it's in front of. * Fix package.ps1 compression. 7z was increasing file size, somehow.
* ~Finish integrating faster-whisperyum2023-04-24
| | | | I'm able to use the new code to show text in game. Not yet play-tested.
* Begin integrating faster-whisperv0.11.0yum2023-04-23
| | | | | | This is a much faster, lower-VRAM reimplementation of Whisper in Python. Early testing is extremely promising: fast transcription speed, extremely low resource usage (CPU/RAM/VRAM), high accuracy.
* package.ps1 always regenerates Python/v0.10.1yum2023-03-28
| | | | Intended to avoid accidentally releasing dirty environments.
* Fix virtual env resetyum2023-03-28
| | | | | | Use `pip freeze` and `pip uninstall` to reset the venv to a near-default state. Filter out `future` since we need to vendor it. If it ever gets removed, the installation is borked.
* Vendor pip and futureyum2023-03-28
| | | | | | | | This dependency fails to install with the embedded python, so now it's vendored. Installing pip after wheel would result in wheel reinstalling, so we also vendor pip.
* Custom chatbox shader writes depthyum2023-03-23
| | | | | | | | This fixes issues where the transparent corners of the textbox render in front of other materials, causing those other materials to skip rendering. * Update README.md with roadmap and avatar resource usage.
* Reduce texture memory usage for English speakersv0.10.0yum2023-03-21
| | | | | | | | | | We used to populate 7 4k textures + 1 2k texture for all users. Now if the user has configured `bytes_per_char=1` in the Unity panel, we just populate a single 512x512 texture containing the first 128 ASCII characters. This reduces texture memory usage by 99.74%, from 134.67 MB to 340 KB.
* Fix _socket module not found issueyum2023-03-21
| | | | | Need python310._pth, specifically 'import site' line, for embedded python + pip to get along.
* Begin work fixing venv setupyum2023-03-09
| | | | | If you don't have Python installed, venv setup will fail. Begin work fixing environment config so `pip install` uses vendored Python.
* Set PYTHONPATH in synchronous multiprocessing layeryum2023-03-08
| | | | | | | | | A user saw an error like `ModuleNotFoundError: No module named _socket`. StackOverflow blames this on PYTHONPATH, so let's try setting it. * Fix latent bug in Scripts/transcribe.py. PyAudio.open() positional parameters must be specified in correct order, even when telling it which parameter is which. *shrug*
* Expose more C++ whisper parameters in GUIyum2023-03-08
| | | | | | | | Expose decode method, beam search parameters, and voice activity detection parameters in GUI. * Remove WhisperCPP::Init(), do it on launch instead. * Add float support to ConfigMarshal
* Silence virtual env setup PATH warningsyum2023-03-06
| | | | | | Twofold approach: * All spawned processes have the desired path (new codepath) * Setup command silences the warning (old codepath)
* Animator generation and dumping mics no longer hang GUIv0.9.0yum2023-03-05
| | | | | | Do these in a std::future. * SetAffinityMask() now returns a value on all control paths
generated by cgit v1.2.3 (git 2.39.1) at 2026-06-01 21:09:25 +0000