Jatin K MalikandGitHub
57a0ddd0b8
* feat(speech): add whisper.cpp with Vulkan support for GPU acceleration Add whisper.cpp as a new speech recognition engine with the following features: - Vulkan GPU acceleration support (AMD, Intel, NVIDIA) - Fallback to CUDA for NVIDIA GPUs - CPU-only mode with automatic thread optimization - Support for all model sizes: tiny, base, small, medium, large - Hardware detection to recommend best model/backend - Models downloaded from Hugging Face (ggml format) - Updated UI to show compute backend info in settings - pywhispercpp as the Python binding library - whisper_cpp as the new default engine Changes: - New whispercpp_model_info.py with model metadata and hardware detection - Updated recognition_manager.py with whisper.cpp init and transcription - Updated settings_dialog.py with whisper.cpp UI support - Updated config_manager.py with whisper_cpp_model_size config - Updated main.py with whisper_cpp CLI option - Updated pyproject.toml with pywhispercpp dependency - Updated install.sh with vulkan-tools for GPU detection Closes #104 * style: fix black and isort formatting issues * test: update config manager test for whisper_cpp default engine * feat(install): interactive mode with 3 engine choices and whisper.cpp as default Major changes to install.sh: - Interactive mode is now the DEFAULT (not --auto) - Added --auto flag for non-interactive automatic installation - New --engine flag to specify engine directly - Interactive mode shows 3 engine options with visual boxes: 1. whisper.cpp (recommended) - Vulkan/CUDA/CPU support 2. whisper (OpenAI) - PyTorch-based, NVIDIA-only 3. VOSK - lightweight option - Hardware detection with recommendations: - Detects Vulkan support (AMD/Intel/NVIDIA) - Detects NVIDIA CUDA - Checks available RAM - Recommends best engine based on hardware - Updated help text with new options and examples - Removed old --with-whisper, --whisper-cpu, --no-whisper flags - whisper.cpp is now the default engine for automatic mode * feat(uninstall): kill running vocalinux processes before uninstall * fix(whisper.cpp): auto-download model, use all CPU cores, hide unavailable engines Three fixes for whisper.cpp implementation: 1. Auto-download model during install - Added install_whispercpp_model() function to install.sh - Downloads ggml-tiny.bin (~39MB) from Hugging Face - Runs automatically when whisper.cpp engine is selected 2. Use all CPU cores for transcription - Added n_threads parameter to Model initialization - Uses multiprocessing.cpu_count() to get all cores - Significantly improves transcription speed 3. Hide unavailable engines from dropdown - Added get_available_engines() function to detect installed engines - Settings dialog now only shows engines that are actually installed - Falls back to first available engine if current not available Fixes user-reported issues with whisper.cpp integration. * ui(settings): display whisper.cpp correctly and increase dialog height - Changed engine display name from 'whisper_cpp' to 'whisper.cpp' - Added format_engine_display_name() helper function - Dialog now uses 75% of screen height for better visibility - More options visible by default without scrolling * revert(settings): remove display name change, keep dialog height increase - Reverted engine display name change (was breaking engine selection) - Kept dialog height at 75% of screen for better visibility * style: fix black and isort formatting for whisper.cpp logging * style: fix black formatting in settings_dialog.py * ci: fix Fedora 39 container package installation Add dnf cache update and fallback with --nogpgcheck for Fedora containers that may have stale or missing package metadata.
381 lines
15 KiB
Python
381 lines
15 KiB
Python
"""
|
|
Tests for the config manager functionality.
|
|
"""
|
|
|
|
import json
|
|
import os
|
|
import tempfile
|
|
import unittest
|
|
from unittest.mock import patch
|
|
|
|
# Update import path to use the new package structure
|
|
from vocalinux.ui.config_manager import DEFAULT_CONFIG, ConfigManager
|
|
|
|
|
|
class TestConfigManager(unittest.TestCase):
|
|
"""Test cases for the configuration manager."""
|
|
|
|
def setUp(self):
|
|
"""Set up test environment."""
|
|
# Create a temporary directory for configuration
|
|
self.temp_dir = tempfile.TemporaryDirectory()
|
|
self.temp_config_dir = os.path.join(self.temp_dir.name, ".config/vocalinux")
|
|
os.makedirs(self.temp_config_dir, exist_ok=True)
|
|
self.temp_config_file = os.path.join(self.temp_config_dir, "config.json")
|
|
|
|
# Patch the config paths to use our temporary directory
|
|
self.config_dir_patcher = patch(
|
|
"vocalinux.ui.config_manager.CONFIG_DIR", self.temp_config_dir
|
|
)
|
|
self.config_file_patcher = patch(
|
|
"vocalinux.ui.config_manager.CONFIG_FILE", self.temp_config_file
|
|
)
|
|
|
|
self.config_dir_patcher.start()
|
|
self.config_file_patcher.start()
|
|
|
|
# Patch logging to avoid actual logging
|
|
self.logger_patcher = patch("vocalinux.ui.config_manager.logger")
|
|
self.mock_logger = self.logger_patcher.start()
|
|
|
|
def tearDown(self):
|
|
"""Clean up after tests."""
|
|
self.config_dir_patcher.stop()
|
|
self.config_file_patcher.stop()
|
|
self.logger_patcher.stop()
|
|
self.temp_dir.cleanup()
|
|
|
|
def test_init_default_config(self):
|
|
"""Test initialization with default configuration."""
|
|
config_manager = ConfigManager()
|
|
self.assertEqual(config_manager.config, DEFAULT_CONFIG)
|
|
self.mock_logger.info.assert_called_with(
|
|
f"Config file not found at {self.temp_config_file}. Using defaults."
|
|
)
|
|
self.assertTrue(os.path.exists(self.temp_config_dir))
|
|
|
|
def test_ensure_config_dir(self):
|
|
"""Test that _ensure_config_dir creates the directory."""
|
|
# Delete the config directory to test creation
|
|
os.rmdir(self.temp_config_dir)
|
|
self.assertFalse(os.path.exists(self.temp_config_dir))
|
|
|
|
# Create config manager, which should create the directory
|
|
ConfigManager()
|
|
self.assertTrue(os.path.exists(self.temp_config_dir))
|
|
|
|
def test_load_config(self):
|
|
"""Test loading configuration from file."""
|
|
# Create a test config file
|
|
test_config = {
|
|
"speech_recognition": {
|
|
"engine": "whisper",
|
|
"model_size": "large",
|
|
},
|
|
"ui": {
|
|
"start_minimized": True,
|
|
},
|
|
}
|
|
|
|
with open(self.temp_config_file, "w") as f:
|
|
json.dump(test_config, f)
|
|
|
|
# Load the config
|
|
config_manager = ConfigManager()
|
|
|
|
# Verify it merged with defaults correctly
|
|
self.assertEqual(config_manager.config["speech_recognition"]["engine"], "whisper")
|
|
self.assertEqual(config_manager.config["speech_recognition"]["model_size"], "large")
|
|
self.assertEqual(
|
|
config_manager.config["speech_recognition"]["vad_sensitivity"], 3
|
|
) # From defaults
|
|
self.assertEqual(config_manager.config["ui"]["start_minimized"], True)
|
|
self.assertEqual(config_manager.config["ui"]["show_notifications"], True) # From defaults
|
|
|
|
def test_load_config_file_error(self):
|
|
"""Test handling of errors when loading config file."""
|
|
# Create a broken config file
|
|
with open(self.temp_config_file, "w") as f:
|
|
f.write("{broken json")
|
|
|
|
# Load the config - with broken JSON, it should use defaults
|
|
config_manager = ConfigManager()
|
|
|
|
# Verify it used defaults - check key structure exists
|
|
self.assertIn("speech_recognition", config_manager.config)
|
|
self.assertIn("engine", config_manager.config["speech_recognition"])
|
|
self.assertIn("ui", config_manager.config)
|
|
|
|
# Verify logger.error was called for the broken JSON
|
|
self.mock_logger.error.assert_called()
|
|
|
|
def test_save_config(self):
|
|
"""Test saving configuration to file."""
|
|
config_manager = ConfigManager()
|
|
|
|
# Modify config
|
|
config_manager.config["speech_recognition"]["engine"] = "whisper"
|
|
config_manager.config["ui"]["start_minimized"] = True
|
|
|
|
# Save config
|
|
result = config_manager.save_config()
|
|
self.assertTrue(result)
|
|
|
|
# Verify file was created with correct content
|
|
self.assertTrue(os.path.exists(self.temp_config_file))
|
|
with open(self.temp_config_file, "r") as f:
|
|
saved_config = json.load(f)
|
|
|
|
self.assertEqual(saved_config["speech_recognition"]["engine"], "whisper")
|
|
self.assertEqual(saved_config["ui"]["start_minimized"], True)
|
|
|
|
def test_save_config_error(self):
|
|
"""Test handling of errors when saving config file."""
|
|
config_manager = ConfigManager()
|
|
|
|
# Mock open to raise an exception
|
|
with patch("builtins.open", side_effect=PermissionError("Permission denied")):
|
|
result = config_manager.save_config()
|
|
self.assertFalse(result)
|
|
self.mock_logger.error.assert_called()
|
|
|
|
def test_get_existing_value(self):
|
|
"""Test getting an existing configuration value from defaults."""
|
|
# Test that DEFAULT_CONFIG constant has the expected default engine
|
|
# Import directly to get the current value (not cached from earlier imports)
|
|
import importlib
|
|
|
|
import vocalinux.ui.config_manager as cm
|
|
|
|
importlib.reload(cm)
|
|
self.assertEqual(
|
|
cm.DEFAULT_CONFIG["speech_recognition"]["engine"], "whisper_cpp"
|
|
) # Default is whisper_cpp for best performance with Vulkan support
|
|
|
|
# Also test the get method works - it should return a valid engine value
|
|
config_manager = ConfigManager()
|
|
value = config_manager.get("speech_recognition", "engine")
|
|
self.assertIn(value, ["vosk", "whisper", "whisper_cpp"]) # Should be one of valid engines
|
|
|
|
def test_get_nonexistent_value(self):
|
|
"""Test getting a nonexistent configuration value."""
|
|
config_manager = ConfigManager()
|
|
value = config_manager.get("nonexistent", "key", "default_value")
|
|
self.assertEqual(value, "default_value")
|
|
|
|
def test_set_existing_section(self):
|
|
"""Test setting a value in an existing section."""
|
|
config_manager = ConfigManager()
|
|
result = config_manager.set("speech_recognition", "engine", "vosk")
|
|
self.assertTrue(result)
|
|
self.assertEqual(config_manager.config["speech_recognition"]["engine"], "vosk")
|
|
|
|
def test_set_new_section(self):
|
|
"""Test setting a value in a new section."""
|
|
config_manager = ConfigManager()
|
|
result = config_manager.set("new_section", "key", "value")
|
|
self.assertTrue(result)
|
|
self.assertEqual(config_manager.config["new_section"]["key"], "value")
|
|
|
|
def test_set_error(self):
|
|
"""Test handling of errors when setting a value."""
|
|
config_manager = ConfigManager()
|
|
config_manager.config = 1 # Not a dict, will cause error
|
|
result = config_manager.set("section", "key", "value")
|
|
self.assertFalse(result)
|
|
self.mock_logger.error.assert_called()
|
|
|
|
def test_update_dict_recursive(self):
|
|
"""Test recursive dictionary update."""
|
|
target = {"a": {"b": 1, "c": 2}, "d": 3}
|
|
|
|
source = {"a": {"b": 10, "e": 20}, "f": 30}
|
|
|
|
config_manager = ConfigManager()
|
|
config_manager._update_dict_recursive(target, source)
|
|
|
|
# Check that values were updated correctly
|
|
self.assertEqual(target["a"]["b"], 10) # Updated
|
|
self.assertEqual(target["a"]["c"], 2) # Unchanged
|
|
self.assertEqual(target["a"]["e"], 20) # Added
|
|
self.assertEqual(target["d"], 3) # Unchanged
|
|
self.assertEqual(target["f"], 30) # Added
|
|
|
|
def test_get_model_size_for_engine(self):
|
|
"""Test getting model size for a specific engine."""
|
|
config_manager = ConfigManager()
|
|
|
|
# Test default values
|
|
self.assertEqual(config_manager.get_model_size_for_engine("vosk"), "small")
|
|
self.assertEqual(config_manager.get_model_size_for_engine("whisper"), "tiny")
|
|
|
|
# Set specific model sizes
|
|
config_manager.set_model_size_for_engine("vosk", "medium")
|
|
config_manager.set_model_size_for_engine("whisper", "small")
|
|
|
|
# Verify they are returned correctly
|
|
self.assertEqual(config_manager.get_model_size_for_engine("vosk"), "medium")
|
|
self.assertEqual(config_manager.get_model_size_for_engine("whisper"), "small")
|
|
|
|
def test_set_model_size_for_engine(self):
|
|
"""Test setting model size for a specific engine."""
|
|
config_manager = ConfigManager()
|
|
|
|
# Set model size for vosk
|
|
config_manager.set_model_size_for_engine("vosk", "large")
|
|
self.assertEqual(config_manager.config["speech_recognition"]["vosk_model_size"], "large")
|
|
self.assertEqual(config_manager.config["speech_recognition"]["model_size"], "large")
|
|
|
|
# Set model size for whisper
|
|
config_manager.set_model_size_for_engine("whisper", "medium")
|
|
self.assertEqual(
|
|
config_manager.config["speech_recognition"]["whisper_model_size"], "medium"
|
|
)
|
|
self.assertEqual(config_manager.config["speech_recognition"]["model_size"], "medium")
|
|
|
|
def test_migrate_old_config(self):
|
|
"""Test migration of old config format without per-engine model sizes."""
|
|
# Create an old-style config file without per-engine model sizes
|
|
old_config = {
|
|
"speech_recognition": {
|
|
"engine": "vosk",
|
|
"model_size": "medium",
|
|
"vad_sensitivity": 3,
|
|
"silence_timeout": 2.0,
|
|
}
|
|
}
|
|
|
|
with open(self.temp_config_file, "w") as f:
|
|
json.dump(old_config, f)
|
|
|
|
# Load the config (should trigger migration)
|
|
config_manager = ConfigManager()
|
|
|
|
# Verify migration added per-engine model sizes
|
|
self.assertEqual(config_manager.config["speech_recognition"]["vosk_model_size"], "medium")
|
|
self.assertEqual(config_manager.config["speech_recognition"]["whisper_model_size"], "tiny")
|
|
|
|
def test_update_speech_recognition_settings_per_engine(self):
|
|
"""Test that update_speech_recognition_settings saves per-engine model sizes."""
|
|
config_manager = ConfigManager()
|
|
|
|
# Update settings for vosk
|
|
config_manager.update_speech_recognition_settings({"engine": "vosk", "model_size": "large"})
|
|
|
|
self.assertEqual(config_manager.config["speech_recognition"]["vosk_model_size"], "large")
|
|
|
|
# Update settings for whisper
|
|
config_manager.update_speech_recognition_settings(
|
|
{"engine": "whisper", "model_size": "small"}
|
|
)
|
|
|
|
self.assertEqual(config_manager.config["speech_recognition"]["whisper_model_size"], "small")
|
|
|
|
# Verify the vosk setting wasn't changed
|
|
self.assertEqual(config_manager.config["speech_recognition"]["vosk_model_size"], "large")
|
|
|
|
def test_save_settings(self):
|
|
"""Test the save_settings method (alias for save_config)."""
|
|
config_manager = ConfigManager()
|
|
|
|
# Modify config
|
|
config_manager.config["speech_recognition"]["engine"] = "vosk"
|
|
|
|
# Save settings
|
|
result = config_manager.save_settings()
|
|
self.assertTrue(result)
|
|
|
|
# Verify file was saved
|
|
self.assertTrue(os.path.exists(self.temp_config_file))
|
|
with open(self.temp_config_file, "r") as f:
|
|
saved_config = json.load(f)
|
|
self.assertEqual(saved_config["speech_recognition"]["engine"], "vosk")
|
|
|
|
def test_get_settings(self):
|
|
"""Test the get_settings method returns the entire config."""
|
|
config_manager = ConfigManager()
|
|
|
|
# Get settings
|
|
settings = config_manager.get_settings()
|
|
|
|
# Verify it returns the config
|
|
self.assertEqual(settings, config_manager.config)
|
|
self.assertIn("speech_recognition", settings)
|
|
self.assertIn("ui", settings)
|
|
|
|
def test_get_model_size_for_engine_with_engine_specific_key(self):
|
|
"""Test getting model size when engine-specific key exists."""
|
|
# Create config with engine-specific model sizes
|
|
test_config = {
|
|
"speech_recognition": {
|
|
"engine": "whisper",
|
|
"vosk_model_size": "medium",
|
|
"whisper_model_size": "small",
|
|
"model_size": "large", # Generic fallback
|
|
}
|
|
}
|
|
|
|
with open(self.temp_config_file, "w") as f:
|
|
json.dump(test_config, f)
|
|
|
|
config_manager = ConfigManager()
|
|
|
|
# Should use engine-specific size, not generic
|
|
self.assertEqual(config_manager.get_model_size_for_engine("vosk"), "medium")
|
|
self.assertEqual(config_manager.get_model_size_for_engine("whisper"), "small")
|
|
|
|
def test_set_model_size_for_engine_new_section(self):
|
|
"""Test setting model size when speech_recognition section doesn't exist."""
|
|
config_manager = ConfigManager()
|
|
|
|
# Remove the speech_recognition section
|
|
del config_manager.config["speech_recognition"]
|
|
|
|
# Set model size - should create the section
|
|
config_manager.set_model_size_for_engine("vosk", "large")
|
|
|
|
# Verify section was created and value was set
|
|
self.assertIn("speech_recognition", config_manager.config)
|
|
self.assertEqual(config_manager.config["speech_recognition"]["vosk_model_size"], "large")
|
|
|
|
def test_get_model_size_for_engine_fallback_to_generic(self):
|
|
"""Test fallback to generic model_size when no engine-specific key exists."""
|
|
# Create config with only generic model_size (no engine-specific)
|
|
test_config = {
|
|
"speech_recognition": {
|
|
"engine": "vosk",
|
|
"model_size": "large",
|
|
# No vosk_model_size or whisper_model_size
|
|
}
|
|
}
|
|
|
|
with open(self.temp_config_file, "w") as f:
|
|
json.dump(test_config, f)
|
|
|
|
config_manager = ConfigManager()
|
|
|
|
# Should fall back to generic model_size
|
|
# Note: migration might add engine-specific keys, so we test this directly
|
|
del config_manager.config["speech_recognition"]["vosk_model_size"]
|
|
del config_manager.config["speech_recognition"]["whisper_model_size"]
|
|
|
|
self.assertEqual(config_manager.get_model_size_for_engine("vosk"), "large")
|
|
self.assertEqual(config_manager.get_model_size_for_engine("whisper"), "large")
|
|
|
|
def test_update_speech_recognition_settings_new_section(self):
|
|
"""Test update_speech_recognition_settings when section doesn't exist."""
|
|
config_manager = ConfigManager()
|
|
|
|
# Remove the speech_recognition section
|
|
del config_manager.config["speech_recognition"]
|
|
|
|
# Update settings - should create the section
|
|
config_manager.update_speech_recognition_settings(
|
|
{"engine": "whisper", "vad_sensitivity": 5}
|
|
)
|
|
|
|
# Verify section was created
|
|
self.assertIn("speech_recognition", config_manager.config)
|
|
self.assertEqual(config_manager.config["speech_recognition"]["engine"], "whisper")
|
|
self.assertEqual(config_manager.config["speech_recognition"]["vad_sensitivity"], 5)
|