pyr0ball
173f7f37d4
Ports prior voice assistant research and prototypes from devl/Devops into the Minerva repo. Includes: - docs/: architecture, wake word guides, ESP32-S3 spec, hardware buying guide - scripts/: voice_server.py, voice_server_enhanced.py, setup scripts - hardware/maixduino/: edge device scripts with WiFi credentials scrubbed (replaced hardcoded password with secrets.py pattern) - config/.env.example: server config template - .gitignore: excludes .env, secrets.py, model blobs, ELF firmware - CLAUDE.md: Minerva product context and connection to cf-voice roadmap
409 lines
11 KiB
Bash
Executable file
409 lines
11 KiB
Bash
Executable file
#!/usr/bin/env bash
|
|
#
|
|
# Path: download_pretrained_models.sh
|
|
#
|
|
# Purpose and usage:
|
|
# Downloads and sets up pre-trained Mycroft Precise wake word models
|
|
# - Downloads Hey Mycroft, Hey Jarvis, and other available models
|
|
# - Tests each model with microphone
|
|
# - Configures voice server to use them
|
|
#
|
|
# Requirements:
|
|
# - Mycroft Precise installed (run setup_precise.sh first)
|
|
# - Internet connection for downloads
|
|
# - Microphone for testing
|
|
#
|
|
# Usage:
|
|
# ./download_pretrained_models.sh [--test-all] [--model MODEL_NAME]
|
|
#
|
|
# Author: PRbL Library
|
|
# Created: $(date +"%Y-%m-%d")
|
|
|
|
# ----- PRbL Color and output functions -----
|
|
RED='\033[0;31m'
|
|
GREEN='\033[0;32m'
|
|
YELLOW='\033[0;33m'
|
|
BLUE='\033[0;34m'
|
|
PURPLE='\033[0;35m'
|
|
CYAN='\033[0;36m'
|
|
NC='\033[0m' # No Color
|
|
|
|
print_status() {
|
|
local level="$1"
|
|
shift
|
|
case "$level" in
|
|
"info") echo -e "${BLUE}[INFO]${NC} $*" >&2 ;;
|
|
"success") echo -e "${GREEN}[SUCCESS]${NC} $*" >&2 ;;
|
|
"warning") echo -e "${YELLOW}[WARNING]${NC} $*" >&2 ;;
|
|
"error") echo -e "${RED}[ERROR]${NC} $*" >&2 ;;
|
|
"debug") [[ "$VERBOSE" == "true" ]] && echo -e "${PURPLE}[DEBUG]${NC} $*" >&2 ;;
|
|
*) echo -e "$*" >&2 ;;
|
|
esac
|
|
}
|
|
|
|
# ----- Configuration -----
|
|
MODELS_DIR="$HOME/precise-models/pretrained"
|
|
TEST_ALL=false
|
|
SPECIFIC_MODEL=""
|
|
VERBOSE=false
|
|
|
|
# Available pre-trained models
|
|
declare -A MODELS=(
|
|
["hey-mycroft"]="https://github.com/MycroftAI/precise-data/raw/models-dev/hey-mycroft.tar.gz"
|
|
["hey-jarvis"]="https://github.com/MycroftAI/precise-data/raw/models-dev/hey-jarvis.tar.gz"
|
|
["christopher"]="https://github.com/MycroftAI/precise-data/raw/models-dev/christopher.tar.gz"
|
|
["hey-ezra"]="https://github.com/MycroftAI/precise-data/raw/models-dev/hey-ezra.tar.gz"
|
|
)
|
|
|
|
# ----- Dependency checking -----
|
|
command_exists() {
|
|
command -v "$1" &> /dev/null
|
|
}
|
|
|
|
check_dependencies() {
|
|
local missing=()
|
|
|
|
if ! command_exists wget; then
|
|
missing+=("wget")
|
|
fi
|
|
|
|
if ! command_exists precise-listen; then
|
|
missing+=("precise-listen (run setup_precise.sh first)")
|
|
fi
|
|
|
|
if [[ ${#missing[@]} -gt 0 ]]; then
|
|
print_status error "Missing dependencies: ${missing[*]}"
|
|
return 1
|
|
fi
|
|
|
|
return 0
|
|
}
|
|
|
|
# ----- Parse arguments -----
|
|
parse_args() {
|
|
while [[ $# -gt 0 ]]; do
|
|
case "$1" in
|
|
--test-all)
|
|
TEST_ALL=true
|
|
shift
|
|
;;
|
|
--model)
|
|
SPECIFIC_MODEL="$2"
|
|
shift 2
|
|
;;
|
|
-v|--verbose)
|
|
VERBOSE=true
|
|
shift
|
|
;;
|
|
-h|--help)
|
|
cat << EOF
|
|
Usage: $(basename "$0") [OPTIONS]
|
|
|
|
Download and test pre-trained Mycroft Precise wake word models
|
|
|
|
Options:
|
|
--test-all Download and test all available models
|
|
--model NAME Download and test specific model
|
|
-v, --verbose Enable verbose output
|
|
-h, --help Show this help message
|
|
|
|
Available models:
|
|
hey-mycroft Original Mycroft wake word (most data)
|
|
hey-jarvis Popular alternative
|
|
christopher Alternative wake word
|
|
hey-ezra Another option
|
|
|
|
Examples:
|
|
$(basename "$0") --model hey-mycroft
|
|
$(basename "$0") --test-all
|
|
|
|
EOF
|
|
exit 0
|
|
;;
|
|
*)
|
|
print_status error "Unknown option: $1"
|
|
exit 1
|
|
;;
|
|
esac
|
|
done
|
|
}
|
|
|
|
# ----- Functions -----
|
|
|
|
create_models_directory() {
|
|
print_status info "Creating models directory: $MODELS_DIR"
|
|
mkdir -p "$MODELS_DIR" || {
|
|
print_status error "Failed to create directory"
|
|
return 1
|
|
}
|
|
return 0
|
|
}
|
|
|
|
download_model() {
|
|
local model_name="$1"
|
|
local model_url="${MODELS[${model_name}]}"
|
|
|
|
if [[ -z "$model_url" ]]; then
|
|
print_status error "Unknown model: $model_name"
|
|
return 1
|
|
fi
|
|
|
|
# Check if already downloaded
|
|
if [[ -f "$MODELS_DIR/${model_name}.net" ]]; then
|
|
print_status info "Model already exists: $model_name"
|
|
return 0
|
|
fi
|
|
|
|
print_status info "Downloading $model_name..."
|
|
|
|
local temp_file="/tmp/${model_name}-$$.tar.gz"
|
|
|
|
wget -q --show-progress -O "$temp_file" "$model_url" || {
|
|
print_status error "Failed to download $model_name"
|
|
rm -f "$temp_file"
|
|
return 1
|
|
}
|
|
|
|
# Extract
|
|
print_status info "Extracting $model_name..."
|
|
tar xzf "$temp_file" -C "$MODELS_DIR" || {
|
|
print_status error "Failed to extract $model_name"
|
|
rm -f "$temp_file"
|
|
return 1
|
|
}
|
|
|
|
rm -f "$temp_file"
|
|
|
|
# Verify extraction
|
|
if [[ -f "$MODELS_DIR/${model_name}.net" ]]; then
|
|
print_status success "Downloaded: $model_name"
|
|
return 0
|
|
else
|
|
print_status error "Extraction failed for $model_name"
|
|
return 1
|
|
fi
|
|
}
|
|
|
|
test_model() {
|
|
local model_name="$1"
|
|
local model_file="$MODELS_DIR/${model_name}.net"
|
|
|
|
if [[ ! -f "$model_file" ]]; then
|
|
print_status error "Model file not found: $model_file"
|
|
return 1
|
|
fi
|
|
|
|
print_status info "Testing model: $model_name"
|
|
echo ""
|
|
echo -e "${CYAN}Instructions:${NC}"
|
|
echo " - Speak the wake word: '$model_name'"
|
|
echo " - You should see '!' when detected"
|
|
echo " - Press Ctrl+C to stop testing"
|
|
echo ""
|
|
read -p "Press Enter to start test..."
|
|
|
|
# Activate conda environment if needed
|
|
if command_exists conda; then
|
|
eval "$(conda shell.bash hook)"
|
|
conda activate precise 2>/dev/null || true
|
|
fi
|
|
|
|
precise-listen "$model_file" || {
|
|
print_status warning "Test interrupted or failed"
|
|
return 1
|
|
}
|
|
|
|
return 0
|
|
}
|
|
|
|
create_multi_wake_config() {
|
|
print_status info "Creating multi-wake-word configuration..."
|
|
|
|
local config_file="$MODELS_DIR/multi-wake-config.sh"
|
|
|
|
cat > "$config_file" << 'EOF'
|
|
#!/bin/bash
|
|
# Multi-wake-word configuration
|
|
# Generated by download_pretrained_models.sh
|
|
|
|
# Start voice server with multiple wake words
|
|
cd ~/voice-assistant
|
|
|
|
# List of wake word models
|
|
MODELS=""
|
|
|
|
EOF
|
|
|
|
# Add each downloaded model to config
|
|
for model_name in "${!MODELS[@]}"; do
|
|
if [[ -f "$MODELS_DIR/${model_name}.net" ]]; then
|
|
echo "# Found: $model_name" >> "$config_file"
|
|
echo "MODELS=\"\${MODELS}${model_name}:$MODELS_DIR/${model_name}.net:0.5,\"" >> "$config_file"
|
|
fi
|
|
done
|
|
|
|
cat >> "$config_file" << 'EOF'
|
|
|
|
# Remove trailing comma
|
|
MODELS="${MODELS%,}"
|
|
|
|
# Activate environment
|
|
eval "$(conda shell.bash hook)"
|
|
conda activate precise
|
|
|
|
# Start server
|
|
python voice_server.py \
|
|
--enable-precise \
|
|
--precise-models "$MODELS" \
|
|
--ha-token "$HA_TOKEN"
|
|
|
|
EOF
|
|
|
|
chmod +x "$config_file"
|
|
|
|
print_status success "Created: $config_file"
|
|
echo ""
|
|
print_status info "To use multiple wake words, run:"
|
|
print_status info " $config_file"
|
|
|
|
return 0
|
|
}
|
|
|
|
list_downloaded_models() {
|
|
print_status info "Downloaded models in $MODELS_DIR:"
|
|
echo ""
|
|
|
|
local count=0
|
|
for model_name in "${!MODELS[@]}"; do
|
|
if [[ -f "$MODELS_DIR/${model_name}.net" ]]; then
|
|
local size=$(du -h "$MODELS_DIR/${model_name}.net" | cut -f1)
|
|
echo -e " ${GREEN}✓${NC} ${model_name}.net (${size})"
|
|
((count++))
|
|
else
|
|
echo -e " ${YELLOW}○${NC} ${model_name}.net (not downloaded)"
|
|
fi
|
|
done
|
|
|
|
echo ""
|
|
print_status success "Total downloaded: $count"
|
|
|
|
return 0
|
|
}
|
|
|
|
compare_models() {
|
|
print_status info "Model comparison:"
|
|
echo ""
|
|
|
|
cat << 'EOF'
|
|
┌─────────────────┬──────────────┬─────────────┬─────────────────┐
|
|
│ Wake Word │ Popularity │ Difficulty │ Recommended For │
|
|
├─────────────────┼──────────────┼─────────────┼─────────────────┤
|
|
│ Hey Mycroft │ ★★★★★ │ Easy │ Default choice │
|
|
│ Hey Jarvis │ ★★★★☆ │ Easy │ Pop culture │
|
|
│ Christopher │ ★★☆☆☆ │ Medium │ Unique name │
|
|
│ Hey Ezra │ ★★☆☆☆ │ Medium │ Alternative │
|
|
└─────────────────┴──────────────┴─────────────┴─────────────────┘
|
|
|
|
Recommendations:
|
|
- Start with: Hey Mycroft (most training data)
|
|
- For media: Hey Jarvis (Plex/entertainment)
|
|
- For uniqueness: Christopher or Hey Ezra
|
|
|
|
Multiple wake words:
|
|
- Use different wake words for different contexts
|
|
- Example: "Hey Mycroft" for commands, "Hey Jarvis" for media
|
|
- Server can run 2-3 models simultaneously
|
|
|
|
EOF
|
|
}
|
|
|
|
# ----- Main -----
|
|
main() {
|
|
print_status info "Mycroft Precise Pre-trained Model Downloader"
|
|
echo ""
|
|
|
|
# Parse arguments
|
|
parse_args "$@"
|
|
|
|
# Check dependencies
|
|
check_dependencies || exit 1
|
|
|
|
# Create directory
|
|
create_models_directory || exit 1
|
|
|
|
# Show comparison
|
|
if [[ -z "$SPECIFIC_MODEL" && "$TEST_ALL" != "true" ]]; then
|
|
compare_models
|
|
echo ""
|
|
print_status info "Use --model <name> to download a specific model"
|
|
print_status info "Use --test-all to download all models"
|
|
echo ""
|
|
list_downloaded_models
|
|
exit 0
|
|
fi
|
|
|
|
# Download models
|
|
if [[ -n "$SPECIFIC_MODEL" ]]; then
|
|
# Download specific model
|
|
download_model "$SPECIFIC_MODEL" || exit 1
|
|
|
|
# Offer to test
|
|
echo ""
|
|
read -p "Test this model now? (y/N): " -n 1 -r
|
|
echo
|
|
if [[ $REPLY =~ ^[Yy]$ ]]; then
|
|
test_model "$SPECIFIC_MODEL"
|
|
fi
|
|
|
|
elif [[ "$TEST_ALL" == "true" ]]; then
|
|
# Download all models
|
|
for model_name in "${!MODELS[@]}"; do
|
|
download_model "$model_name"
|
|
echo ""
|
|
done
|
|
|
|
# Offer to test each
|
|
echo ""
|
|
print_status success "All models downloaded"
|
|
echo ""
|
|
read -p "Test each model? (y/N): " -n 1 -r
|
|
echo
|
|
if [[ $REPLY =~ ^[Yy]$ ]]; then
|
|
for model_name in "${!MODELS[@]}"; do
|
|
if [[ -f "$MODELS_DIR/${model_name}.net" ]]; then
|
|
echo ""
|
|
test_model "$model_name"
|
|
fi
|
|
done
|
|
fi
|
|
fi
|
|
|
|
# List results
|
|
echo ""
|
|
list_downloaded_models
|
|
|
|
# Create multi-wake config if multiple models
|
|
local model_count=$(find "$MODELS_DIR" -name "*.net" | wc -l)
|
|
if [[ $model_count -gt 1 ]]; then
|
|
echo ""
|
|
create_multi_wake_config
|
|
fi
|
|
|
|
# Final instructions
|
|
echo ""
|
|
print_status success "Setup complete!"
|
|
echo ""
|
|
print_status info "Next steps:"
|
|
print_status info "1. Test a model: precise-listen $MODELS_DIR/hey-mycroft.net"
|
|
print_status info "2. Use in server: python voice_server.py --enable-precise --precise-model $MODELS_DIR/hey-mycroft.net"
|
|
print_status info "3. Fine-tune: precise-train -e 30 custom.net . --from-checkpoint $MODELS_DIR/hey-mycroft.net"
|
|
|
|
if [[ $model_count -gt 1 ]]; then
|
|
echo ""
|
|
print_status info "For multiple wake words:"
|
|
print_status info " $MODELS_DIR/multi-wake-config.sh"
|
|
fi
|
|
}
|
|
|
|
# Run main
|
|
main "$@"
|