scott
fe3c77ff4f
- Base image: rocm/dev-ubuntu-22.04:6.1 → 7.2 - Python 3.10 → 3.11 via deadsnakes PPA - torch/torchaudio: 2.5.1 → 2.11.0 - torchvision: 0.20.1 → 0.26.0 - pytorch_triton_rocm: 3.1.0 → 3.3.0 - transformers: 4.46.3 → >=4.50.0 - diffusers: 0.29.0 → >=0.32.0 - safetensors: >=0.4.1 → >=0.4.5 - config: temperature 0.8→0.9, seed 0→1960 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
30 lines
793 B
YAML
30 lines
793 B
YAML
model:
|
|
# Options: chatterbox, chatterbox-turbo
|
|
repo_id: chatterbox-turbo
|
|
|
|
tts_engine:
|
|
# Device: cuda, cpu, or leave empty for auto-detect
|
|
device: ""
|
|
predefined_voices_path: voices
|
|
reference_audio_path: reference_audio
|
|
# Fallback voice (stem name, e.g. "default" matches default.wav)
|
|
default_voice_id: default.wav
|
|
|
|
generation_defaults:
|
|
# Turbo model: uses temperature only (exaggeration/cfg_weight ignored)
|
|
# Standard model: uses exaggeration and cfg_weight (temperature ignored)
|
|
temperature: 0.9
|
|
exaggeration: 0.5
|
|
cfg_weight: 0.5
|
|
# seed: 0 = random each call, >0 = reproducible output
|
|
seed: 1960
|
|
|
|
wyoming:
|
|
host: "0.0.0.0"
|
|
port: 10200
|
|
# Max characters per synthesis chunk (split at sentence boundaries)
|
|
chunk_size: 120
|
|
|
|
paths:
|
|
model_cache: /app/hf_cache
|