v0.27.3

What's Changed

Features

• Return sentence level timestamps for multi-sentence input by @santosh-r24 in #520 (documentation)

Fixes

• Support Pytorch 2.9 by @eginhard in #525
• fix(xtts): update streaming code to transformers>=4.57 by @eginhard in #505
• fix(xtts): add over limit text display by @zkhan122 in #495
• Handle romanization for Fairseq models by @eginhard in #506
• docs(formatters): show expected metadata format, improve error handling by @eginhard in #511 (documentation)
• fix(bark): ensure tensors are on same device when not using reference audio by @eginhard in #512
• fix(audio): create parent folders, improve error message by @eginhard in #513
• fix(docker): correct torch backend selection by @eginhard in #524
• Replace jieba with spacy_pkuseg for Chinese word segmentation by @langfod in #504

New Contributors

• @langfod made their first contribution in #504
• @zkhan122 made their first contribution in #495
• @santosh-r24 made their first contribution in #520

Full Changelog: v0.27.2...v0.27.3