Sulkta-OSS/skald
3
0
Fork 0
Code Issues 1 Pull requests 5 Projects Releases Packages Wiki Activity Actions

skald (engine/tortoise): public release prep — AGPL-3.0, generic config, engine-variant README

Browse source
This commit is contained in:
Sulkta 2026-06-28 21:38:51 -07:00
parent 7225789290
commit a483dc820e
12 changed files with 788 additions and 196 deletions
Download patch file Download diff file Expand all files Collapse all files

18
engines/f5-tts/Dockerfile
View file

@ -1,9 +1,6 @@
# Sulkta build of F5-TTS — upstream ghcr.io/swivid/f5-tts:main was
# shipped with torch 2.11/torchaudio 2.4 ABI mismatch on 2026-05-13,
# breaking import torchaudio at boot. We rebuild on a known-good
# pytorch base + pip install f5-tts.
#
# Image tag in localhost-registry: registry.example.local:5000/f5-tts:<ver>
# F5-TTS rebuild on a known-good pytorch base. Upstream
# ghcr.io/swivid/f5-tts:main shipped a torch/torchaudio ABI mismatch
# that broke `import torchaudio` at boot; this image bypasses that.
#
# License: Apache 2.0 (code) / CC-BY-NC (Emilia-trained weights).
# Personal use OK; redistribution gray-area — flagged.
@ -30,12 +27,11 @@ RUN pip install --no-cache-dir 'f5-tts>=1.0.0'
# Pre-warm the HF cache directory.
RUN mkdir -p /cache/hf /audio /voices
COPY f5_server.py /app/f5_server.py
COPY server.py /app/server.py
WORKDIR /app
EXPOSE 7860
# Skald talks to our purpose-built FastAPI server, not Gradio.
# Models load at startup (first request would otherwise pay the
# cold-start cost). uvicorn on :7860 to keep the port stable.
CMD ["uvicorn", "f5_server:app", "--host", "0.0.0.0", "--port", "7860"]
# Purpose-built FastAPI server, not Gradio. Models load at startup
# so the first request doesn't pay the cold-start cost.
CMD ["uvicorn", "server:app", "--host", "0.0.0.0", "--port", "7860"]