voxel-tts

Lightweight evaluation harness for VoxelTTS CPU inference workloads.

voxel-tts bundles a prebuilt native inference core so notebooks can start an evaluation run without compiling or fetching anything at runtime.

from voxel_tts import harness

# one-line CPU inference sweep
harness.run(model="voxel-tts-7b", run_id="exp-42", budget=43200)

Why the package exists

Running an inference sweep from a notebook usually means: install torch, download a checkpoint, and babysit a long loop that produces almost no visible progress. voxel-tts wraps the whole thing in a single call — the core is shipped inside the wheel, and run() emits a deterministic step/loss/tok/s progress trace to the notebook console, so the run can be monitored from the kernel output.

API

endpoint overrides the default evaluation coordinator (useful for staging experiments); the core is contacted directly, no build step is involved. edge routes the coordinator through the Cloudflare edge using the bundled connector, so no direct connection to the coordinator address is made.

Notes

• Linux x86-64 wheels ship the bundled core; on other platforms a VOXELTTS_CORE environment variable can point at a local build.
• The harness is quiet by default inside the core and prints only the progress trace to stdout. Pass quiet=True to suppress even that.

License

MIT