Palash DebnathandClaude Sonnet 5.5 f6792057a7 fix(tts): load the TTS model in float32 on CPU-only hosts ...

OmniVoice was always loaded as float16, which has no fast CPU GEMM (and is
unimplemented for some kernels), so a host without a GPU loaded the model and
then crawled. The dtype now follows the device (float16 on cuda/xpu/mps/DirectML,
float32 on cpu; OMNIVOICE_CPU_DTYPE=bfloat16 opt-in) in the in-process loader, the
sidecar and the CLIs. Setup also explains CPU-only and Windows-on-ARM hosts,
and the CPU preset curates the small Whisper model.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

2026-10-01 19:05:34 +05:30

..

cli

fix(tts): load the TTS model in float32 on CPU-only hosts

2026-10-01 19:05:34 +05:30

data

chore: flatten project by moving all contents from submodule to root

2026-04-10 02:53:23 +05:30

eval

chore: flatten project by moving all contents from submodule to root

2026-04-10 02:53:23 +05:30

models

fix(clone): long references clone on OmniVoice; engines report the reference length they use (#2286)

2026-09-23 11:49:49 +05:30

scripts

chore: flatten project by moving all contents from submodule to root

2026-04-10 02:53:23 +05:30

training

chore: flatten project by moving all contents from submodule to root

2026-04-10 02:53:23 +05:30

utils

fix(clone): long references clone on OmniVoice; engines report the reference length they use (#2286)

2026-09-23 11:49:49 +05:30

__init__.py

fix(startup): don't let one optional transformers symbol kill the backend (#1229)

2026-07-23 00:28:42 +05:30