Ethanfel
f7a6f7790d
Modernized MisoTTS integration for ComfyUI with no torchtune/moshi: - vendored plain-torch Llama backbone (csm_llama), parity-verified Δ=0 vs torchtune - transformers.MimiModel codec (bit-identical codes to moshi), drops moshi/bnb/sphn - low-memory loader: streams 32GB fp32 checkpoint to GPU in bf16 (~18GB VRAM) - nodes: Model Loader, Generate (audiobook chunking + voice anchoring), EPUB Loader - pin-free requirements; runs on modern torch / Blackwell GPUs Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
6 lines
195 B
Python
6 lines
195 B
Python
from .loader import MisoTTSModelLoader
|
|
from .generator import MisoTTSGenerate
|
|
from .epub_loader import MisoTTSEpubLoader
|
|
|
|
__all__ = ["MisoTTSModelLoader", "MisoTTSGenerate", "MisoTTSEpubLoader"]
|