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>
27 lines
557 B
Plaintext
27 lines
557 B
Plaintext
# Wake word
|
||
openwakeword==0.6.0
|
||
|
||
# STT — стриминг с Silero VAD
|
||
RealtimeSTT==0.3.104
|
||
|
||
# TTS — Silero V4 для русского языка
|
||
RealtimeTTS==0.6.1
|
||
torch>=2.0.0 # нужен для Silero (CPU inference)
|
||
|
||
# Agent framework
|
||
smolagents==1.11.0
|
||
ollama==0.4.4 # официальный Python клиент Ollama
|
||
|
||
# Память и конфиг
|
||
pyyaml==6.0.2
|
||
loguru==0.7.2
|
||
|
||
# Аудио
|
||
sounddevice>=0.5.0
|
||
pydub>=0.25.1
|
||
imageio-ffmpeg>=0.6.0
|
||
|
||
# Инструменты агента
|
||
psutil==6.0.0
|
||
pyautogui==0.9.54
|