Same inaSpeechSegmenter engine split into reusable core/ (fftools, segmenter, exporters) + utils/ and a CustomTkinter multi-tab UI. Adds JSON and ffmpeg-script export. Extracted from the stream_tools app.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Wraps detect_singing to process whole folders of recordings at once: --recursive, --pattern, --output-dir, --auto-cut.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Adopts inaSpeechSegmenter (singing classified as music). Full argparse CLI: gap-merge nearby segments, min-duration filter, EDL + CSV export. Engine that all later versions keep.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Switches inference to a transformers pipeline (+pyannote segments), adds overlapping-chunk processing and CSV timecode export for DaVinci.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
HuggingFace matthijs/svd (torch.jit) model + ffmpeg audio extract + tkinter file picker. Proves the concept in one script.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
