Daniil Klimov
110d9cde29
- Fix install_mac.sh: use venv + Python 3.12 (3.14 incompatible with ML libs) - Fix run_mac.sh: activate venv, add CPU thread optimization env vars - Fix agent.py: remove f-string from SYSTEM_PROMPT template (NameError on import) - Add missing deps: sounddevice, pydub, imageio-ffmpeg, omegaconf - Optimize for M1: torch.inference_mode, set_num_threads, OMP/MKL tuning - Switch to qwen2.5:3b for faster LLM responses on Mac - Switch Whisper to medium model with auto compute (small+int8 had poor Russian) - Add initial_prompt for better Russian transcription - Add open_app tool for native macOS app launching - Fix TTS: sanitize Latin text to Cyrillic for Silero compatibility - Fix wake word echo: add cooldown after TTS, reset model state, raise threshold - Make "Слушаю" TTS synchronous to avoid mic interference - Fix train Dockerfile: remove tensorflow/onnx2tf (only ONNX needed), fix deps - Fix train.sh: use wget for dataset download, add --shm-size=2g - Add trained hey_cosmo.onnx wake word model - Add TODO section to CLAUDE.md (ChatterBox TTS, Ollama Modelfile ideas) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
34 lines
1.2 KiB
YAML
34 lines
1.2 KiB
YAML
assistant:
|
|
name: Cosmo
|
|
wake_word: "cosmo"
|
|
|
|
audio:
|
|
sample_rate: 16000
|
|
silence_duration: 1.0
|
|
|
|
whisper:
|
|
model_size: "medium" # medium — лучшее качество русского на CPU (small слишком много ошибок)
|
|
device: "cpu" # Mac Intel/Apple Silicon — CPU (MPS пока не стабилен в faster-whisper)
|
|
compute_type: "auto" # auto вместо int8 — int8 слишком сильно режет качество русского
|
|
language: "ru"
|
|
initial_prompt: "Cosmo, открой браузер, найди программу, запусти приложение." # подсказка для русского контекста
|
|
|
|
ollama:
|
|
base_url: "http://localhost:11434"
|
|
model: "qwen2.5:3b" # 3b быстрее на M1 (~2x), достаточно для голосовых команд
|
|
temperature: 0.2
|
|
max_tokens: 1024
|
|
max_agent_steps: 10
|
|
|
|
performance:
|
|
num_threads: 4 # CPU потоки для torch (TTS/Whisper)
|
|
|
|
tts:
|
|
enabled: true
|
|
silero_speaker: "eugene" # xenia (женский) baya aidar eugene kseniya
|
|
sample_rate: 48000
|
|
|
|
logging:
|
|
level: "INFO"
|
|
file: "logs/cosmo.log"
|