fish-speech · Issues· 15 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #1325
Conversation.visualize exposes unsupported use_color and merge_audio_tokens parameters
bugstaleUpdated Sep 17, 2026 - #1324
Verify evals on Papers with Code
staleUpdated Sep 14, 2026 - #1334
`torch` resolves to 2.14.0 (PyPI) or 2.13.0+cu129 (download.pytorch.org/whl/cu129) depending on install path (pip install .)
bugUpdated Sep 12, 2026 - #1321
Improve Punjabi pronunciation through diacritic-aware Latin transliteration or G2P
enhancementstaleUpdated Sep 10, 2026 - #1320
Punjabi Gurmukhi input appears to mishandle addak and nasalization markers
bugUpdated Sep 8, 2026 - #1308
C++/GGML based Fish Audio S2 Pro in audio.cpp. 3x faster than real time
enhancementUpdated Aug 28, 2026