v1.0.1 updates and polish

src/core/config.py

@@ -16,6 +16,7 @@ from src.core.paths import get_base_path
 # Default Configuration
 DEFAULT_SETTINGS = {
     "hotkey": "f8",
+    "hotkey_translate": "f10",
     "model_size": "small",
     "input_device": None,       # Device ID (int) or Name (str), None = Default
     "save_recordings": False,   # Save .wav files for debugging
@@ -38,6 +39,7 @@ DEFAULT_SETTINGS = {
     
     # AI - Advanced
     "language": "auto",         # "auto" or ISO code
+    "task": "transcribe",       # "transcribe" or "translate" (to English)
     "compute_device": "auto",   # "auto", "cuda", "cpu"
     "compute_type": "int8",     # "int8", "float16", "float32"
     "beam_size": 5,

src/core/hotkey_manager.py

@@ -30,15 +30,16 @@ class HotkeyManager(QObject):
     
     triggered = Signal()
 
-    def __init__(self, hotkey: str = "f8"):
+    def __init__(self, config_key: str = "hotkey"):
         """
         Initialize the HotkeyManager.
 
         Args:
-            hotkey (str): The global hotkey string description. Default: "f8".
+            config_key (str): The configuration key to look up (e.g. "hotkey").
         """
         super().__init__()
-        self.hotkey = hotkey
+        self.config_key = config_key
+        self.hotkey = "f8" # Placeholder
         self.is_listening = False
         self._enabled = True
 
@@ -58,9 +59,9 @@ class HotkeyManager(QObject):
             
         from src.core.config import ConfigManager
         config = ConfigManager()
-        self.hotkey = config.get("hotkey")
+        self.hotkey = config.get(self.config_key)
         
-        logging.info(f"Registering global hotkey: {self.hotkey}")
+        logging.info(f"Registering global hotkey ({self.config_key}): {self.hotkey}")
         try:
             # We don't suppress=True here because we want the app to see keys during recording 
             # (Wait, actually if we are recording we WANT keyboard to see it, 

src/core/languages.py

@@ -0,0 +1,120 @@
+"""
+Supported Languages Module
+==========================
+Full list of languages supported by OpenAI Whisper.
+Maps ISO codes to display names.
+"""
+
+LANGUAGES = {
+    "auto": "Auto Detect",
+    "af": "Afrikaans",
+    "sq": "Albanian",
+    "am": "Amharic",
+    "ar": "Arabic",
+    "hy": "Armenian",
+    "as": "Assamese",
+    "az": "Azerbaijani",
+    "ba": "Bashkir",
+    "eu": "Basque",
+    "be": "Belarusian",
+    "bn": "Bengali",
+    "bs": "Bosnian",
+    "br": "Breton",
+    "bg": "Bulgarian",
+    "my": "Burmese",
+    "ca": "Catalan",
+    "zh": "Chinese",
+    "hr": "Croatian",
+    "cs": "Czech",
+    "da": "Danish",
+    "nl": "Dutch",
+    "en": "English",
+    "et": "Estonian",
+    "fo": "Faroese",
+    "fi": "Finnish",
+    "fr": "French",
+    "gl": "Galician",
+    "ka": "Georgian",
+    "de": "German",
+    "el": "Greek",
+    "gu": "Gujarati",
+    "ht": "Haitian",
+    "ha": "Hausa",
+    "haw": "Hawaiian",
+    "he": "Hebrew",
+    "hi": "Hindi",
+    "hu": "Hungarian",
+    "is": "Icelandic",
+    "id": "Indonesian",
+    "it": "Italian",
+    "ja": "Japanese",
+    "jw": "Javanese",
+    "kn": "Kannada",
+    "kk": "Kazakh",
+    "km": "Khmer",
+    "ko": "Korean",
+    "lo": "Lao",
+    "la": "Latin",
+    "lv": "Latvian",
+    "ln": "Lingala",
+    "lt": "Lithuanian",
+    "lb": "Luxembourgish",
+    "mk": "Macedonian",
+    "mg": "Malagasy",
+    "ms": "Malay",
+    "ml": "Malayalam",
+    "mt": "Maltese",
+    "mi": "Maori",
+    "mr": "Marathi",
+    "mn": "Mongolian",
+    "ne": "Nepali",
+    "no": "Norwegian",
+    "oc": "Occitan",
+    "pa": "Punjabi",
+    "ps": "Pashto",
+    "fa": "Persian",
+    "pl": "Polish",
+    "pt": "Portuguese",
+    "ro": "Romanian",
+    "ru": "Russian",
+    "sa": "Sanskrit",
+    "sr": "Serbian",
+    "sn": "Shona",
+    "sd": "Sindhi",
+    "si": "Sinhala",
+    "sk": "Slovak",
+    "sl": "Slovenian",
+    "so": "Somali",
+    "es": "Spanish",
+    "su": "Sundanese",
+    "sw": "Swahili",
+    "sv": "Swedish",
+    "tl": "Tagalog",
+    "tg": "Tajik",
+    "ta": "Tamil",
+    "tt": "Tatar",
+    "te": "Telugu",
+    "th": "Thai",
+    "bo": "Tibetan",
+    "tr": "Turkish",
+    "tk": "Turkmen",
+    "uk": "Ukrainian",
+    "ur": "Urdu",
+    "uz": "Uzbek",
+    "vi": "Vietnamese",
+    "cy": "Welsh",
+    "yi": "Yiddish",
+    "yo": "Yoruba",
+}
+
+def get_language_names():
+    return list(LANGUAGES.values())
+
+def get_code_by_name(name):
+    for code, lang in LANGUAGES.items():
+        if lang == name:
+            return code
+    return "auto"
+
+def get_name_by_code(code):
+    return LANGUAGES.get(code, "Auto Detect")

src/core/transcriber.py

@@ -74,11 +74,11 @@ class WhisperTranscriber:
             logging.error(f"Failed to load model: {e}")
             self.model = None
 
-    def transcribe(self, audio_data, is_file: bool = False) -> str:
+    def transcribe(self, audio_data, is_file: bool = False, task: Optional[str] = None) -> str:
         """
         Transcribe audio data.
         """
-        logging.info(f"Starting transcription... (is_file={is_file})")
+        logging.info(f"Starting transcription... (is_file={is_file}, task={task})")
         
         # Ensure model is loaded
         if not self.model:
@@ -91,6 +91,10 @@ class WhisperTranscriber:
             beam_size = int(self.config.get("beam_size"))
             best_of = int(self.config.get("best_of"))
             vad = False if is_file else self.config.get("vad_filter")
+            language = self.config.get("language")
+            
+            # Use task override if provided, otherwise config
+            final_task = task if task else self.config.get("task")
             
             # Transcribe
             segments, info = self.model.transcribe(
@@ -98,6 +102,8 @@ class WhisperTranscriber:
                 beam_size=beam_size,
                 best_of=best_of,
                 vad_filter=vad,
+                task=final_task,
+                language=language if language != "auto" else None,
                 vad_parameters=dict(min_silence_duration_ms=500),
                 condition_on_previous_text=self.config.get("condition_on_previous_text"),
                 without_timestamps=True