Ethanfel 33b3d62d02 fix: tagged_speakers splits on single newlines, not just double newlines ...

Each line starting with [Tag] now begins a new segment so users don't need
blank lines between tagged speeches. Continuation lines (no tag) are joined
to the previous tagged segment for multi-line speeches.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-04-06 09:16:54 +02:00

..

__init__.py

feat: add multi-speaker generation with JS-powered dynamic slots

2026-04-06 09:08:23 +02:00

epub_loader.py

Preserve paragraph breaks in EPUB text extraction

2026-04-05 18:06:41 +02:00

generator.py

fix: tagged_speakers splits on single newlines, not just double newlines

2026-04-06 09:16:54 +02:00

loader.py

feat: add torch.compile option to Model Loader

2026-04-05 19:16:39 +02:00

mix_voices.py

fix: only catch ImportError in _resample torchaudio fallback

2026-04-05 19:05:22 +02:00

multi_speaker.py

feat: add multi-speaker generation with JS-powered dynamic slots

2026-04-06 09:08:23 +02:00

voice_design.py

simplify: remove language param entirely — model detects from instruct string

2026-04-05 20:44:27 +02:00

voice_presets.py

Expand voice presets to 8 voices (3 female, 5 male)

2026-04-05 18:51:43 +02:00