RealTimeSTT 0.3.3__tar.gz → 0.3.5__tar.gz

{realtimestt-0.3.3 → realtimestt-0.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RealtimeSTT
-Version: 0.3.3
+Version: 0.3.5
 Summary: A fast Voice Activity Detection and Transcription System
 Home-page: https://github.com/KoljaB/RealTimeSTT
 Author: Kolja Beigel
@@ -55,7 +55,7 @@ https://github.com/user-attachments/assets/797e6552-27cd-41b1-a7f3-e5cbc72094f5
 
 ### Updates
 
-Latest Version: v0.3.3
+Latest Version: v0.3.5
 
 See [release history](https://github.com/KoljaB/RealtimeSTT/releases).
 

{realtimestt-0.3.3 → realtimestt-0.3.5}/README.md

@@ -28,7 +28,7 @@ https://github.com/user-attachments/assets/797e6552-27cd-41b1-a7f3-e5cbc72094f5
 
 ### Updates
 
-Latest Version: v0.3.3
+Latest Version: v0.3.5
 
 See [release history](https://github.com/KoljaB/RealtimeSTT/releases).
 

{realtimestt-0.3.3 → realtimestt-0.3.5}/RealtimeSTT.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RealtimeSTT
-Version: 0.3.3
+Version: 0.3.5
 Summary: A fast Voice Activity Detection and Transcription System
 Home-page: https://github.com/KoljaB/RealTimeSTT
 Author: Kolja Beigel
@@ -55,7 +55,7 @@ https://github.com/user-attachments/assets/797e6552-27cd-41b1-a7f3-e5cbc72094f5
 
 ### Updates
 
-Latest Version: v0.3.3
+Latest Version: v0.3.5
 
 See [release history](https://github.com/KoljaB/RealtimeSTT/releases).
 

realtimestt-0.3.5/RealtimeSTT.egg-info/SOURCES.txt

@@ -0,0 +1,16 @@
+LICENSE
+README.md
+setup.py
+RealtimeSTT/__init__.py
+RealtimeSTT/audio_recorder.py
+RealtimeSTT/audio_recorder_client.py
+RealtimeSTT.egg-info/PKG-INFO
+RealtimeSTT.egg-info/SOURCES.txt
+RealtimeSTT.egg-info/dependency_links.txt
+RealtimeSTT.egg-info/entry_points.txt
+RealtimeSTT.egg-info/requires.txt
+RealtimeSTT.egg-info/top_level.txt
+RealtimeSTT_server/__init__.py
+RealtimeSTT_server/install_packages.py
+RealtimeSTT_server/stt_cli_client.py
+RealtimeSTT_server/stt_server.py

realtimestt-0.3.5/RealtimeSTT.egg-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+stt = RealtimeSTT_server.stt_cli_client:main
+stt-server = RealtimeSTT_server.stt_server:main

realtimestt-0.3.5/RealtimeSTT.egg-info/top_level.txt

@@ -0,0 +1,2 @@
+RealtimeSTT
+RealtimeSTT_server

realtimestt-0.3.3/server/stt_cli_client - Kopie (5).py → realtimestt-0.3.5/RealtimeSTT_server/stt_cli_client.py

@@ -1,20 +1,21 @@
-import os
-import sys
-import pyaudio
-import numpy as np
+from urllib.parse import urlparse
 from scipy import signal
-import logging
+from queue import Queue
+import numpy as np
+import subprocess
+import threading
 import websocket
 import argparse
-import json
-import threading
-import time
+import pyaudio
+import logging
 import struct
 import socket
 import shutil
-from urllib.parse import urlparse
 import queue 
-from queue import Queue
+import json
+import time
+import sys
+import os
 
 os.environ['ALSA_LOG_LEVEL'] = 'none'
 
@@ -23,8 +24,8 @@ CHUNK = 1024
 FORMAT = pyaudio.paInt16
 CHANNELS = 1
 RATE = 44100
-DEFAULT_CONTROL_URL = "ws://localhost:8011"
-DEFAULT_DATA_URL = "ws://localhost:8012"
+DEFAULT_CONTROL_URL = "ws://127.0.0.1:8011"
+DEFAULT_DATA_URL = "ws://127.0.0.1:8012"
 
 # Initialize colorama
 from colorama import init, Fore, Style
@@ -38,8 +39,9 @@ class STTWebSocketClient:
         self.control_url = control_url
         self.data_url = data_url
         self.control_ws = None
-        self.data_ws = None
-        self.is_running = False
+        self.data_ws_app = None
+        self.data_ws_connected = None  # WebSocket object that will be used for sending
+        self.is_running = True
         self.debug = debug
         self.file_output = file_output
         self.last_text = ""
@@ -71,7 +73,6 @@ class STTWebSocketClient:
             self.debug_print("Cannot start STT server. Exiting.")
             return False
 
-        # websocket.enableTrace(self.debug)
         try:
             # Connect to control WebSocket
             self.control_ws = websocket.WebSocketApp(self.control_url,
@@ -85,13 +86,13 @@ class STTWebSocketClient:
             self.control_ws_thread.start()
 
             # Connect to data WebSocket
-            self.data_ws = websocket.WebSocketApp(self.data_url,
-                                                  on_message=self.on_data_message,
-                                                  on_error=self.on_error,
-                                                  on_close=self.on_close,
-                                                  on_open=self.on_data_open)
+            self.data_ws_app = websocket.WebSocketApp(self.data_url,
+                                                      on_message=self.on_data_message,
+                                                      on_error=self.on_error,
+                                                      on_close=self.on_close,
+                                                      on_open=self.on_data_open)
 
-            self.data_ws_thread = threading.Thread(target=self.data_ws.run_forever)
+            self.data_ws_thread = threading.Thread(target=self.data_ws_app.run_forever)
             self.data_ws_thread.daemon = False  # Set to False to ensure proper shutdown
             self.data_ws_thread.start()
 
@@ -113,7 +114,7 @@ class STTWebSocketClient:
 
     def on_data_open(self, ws):
         self.debug_print("Data WebSocket connection opened.")
-        self.is_running = True
+        self.data_ws_connected = ws  # Store the connected websocket object for sending data
         self.start_recording()
 
     def on_error(self, ws, error):
@@ -139,8 +140,57 @@ class STTWebSocketClient:
         if os.name == 'nt':  # Windows
             subprocess.Popen('start /min cmd /c stt-server', shell=True)
         else:  # Unix-like systems
-            subprocess.Popen(['stt-server'], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, start_new_session=True)
-        print("STT server start command issued. Please wait a moment for it to initialize.", file=sys.stderr)
+            terminal_emulators = [
+                'gnome-terminal',
+                'x-terminal-emulator',
+                'konsole',
+                'xfce4-terminal',
+                'lxterminal',
+                'xterm',
+                'mate-terminal',
+                'terminator',
+                'tilix',
+                'alacritty',
+                'urxvt',
+                'eterm',
+                'rxvt',
+                'kitty',
+                'hyper'
+            ]
+
+            terminal = None
+            for term in terminal_emulators:
+                if shutil.which(term):
+                    terminal = term
+                    break
+
+            if terminal:
+                terminal_exec_options = {
+                    'x-terminal-emulator': ['--'],
+                    'gnome-terminal': ['--'],
+                    'mate-terminal': ['--'],
+                    'terminator': ['--'],
+                    'tilix': ['--'],
+                    'konsole': ['-e'],
+                    'xfce4-terminal': ['-e'],
+                    'lxterminal': ['-e'],
+                    'alacritty': ['-e'],
+                    'xterm': ['-e'],
+                    'rxvt': ['-e'],
+                    'urxvt': ['-e'],
+                    'eterm': ['-e'],
+                    'kitty': [],
+                    'hyper': ['--command']
+                }
+
+                exec_option = terminal_exec_options.get(terminal, None)
+                if exec_option is not None:
+                    subprocess.Popen([terminal] + exec_option + ['stt-server'], start_new_session=True)
+                    print(f"STT server started in a new terminal window using {terminal}.", file=sys.stderr)
+                else:
+                    print(f"Unsupported terminal emulator '{terminal}'. Please start the STT server manually.", file=sys.stderr)
+            else:
+                print("No supported terminal emulator found. Please start the STT server manually.", file=sys.stderr)
 
     def ensure_server_running(self):
         if not self.is_server_running():
@@ -161,14 +211,11 @@ class STTWebSocketClient:
                 return False
         return True
 
-    # Handle control messages like set_parameter, get_parameter, etc.
     def on_control_message(self, ws, message):
         try:
             data = json.loads(message)
-            # Handle server response with status
             if 'status' in data:
                 if data['status'] == 'success':
-                    # print(f"Server Response: {data.get('message', '')}")
                     if 'parameter' in data and 'value' in data:
                         print(f"Parameter {data['parameter']} = {data['value']}")
                 elif data['status'] == 'error':
@@ -180,19 +227,16 @@ class STTWebSocketClient:
         except Exception as e:
             self.debug_print(f"Error processing control message: {e}")
 
-    # Handle real-time transcription and full sentence updates
     def on_data_message(self, ws, message):
         try:
             data = json.loads(message)
-            # Handle real-time transcription updates
-            if data.get('type') == 'realtime':
+            message_type = data.get('type')
+            if message_type == 'realtime':
                 if data['text'] != self.last_text:
                     self.last_text = data['text']
                     if not self.norealtime:
                         self.update_progress_bar(self.last_text)
-
-            # Handle full sentences
-            elif data.get('type') == 'fullSentence':
+            elif message_type == 'fullSentence':
                 if self.file_output:
                     sys.stderr.write('\r\033[K')
                     sys.stderr.write(data['text'])
@@ -204,6 +248,16 @@ class STTWebSocketClient:
                     self.finish_progress_bar()
                     print(f"{data['text']}")
                 self.stop()
+            elif message_type in {
+                'vad_detect_start',
+                'vad_detect_stop',
+                'recording_start',
+                'recording_stop',
+                'wakeword_detected',
+                'wakeword_detection_start',
+                'wakeword_detection_end',
+                'transcription_start'}:
+                pass  # Known message types, no action needed
 
             else:
                 self.debug_print(f"Unknown data message format: {data}")
@@ -248,10 +302,11 @@ class STTWebSocketClient:
         self.finish_progress_bar()
         self.is_running = False
         self.stop_event.set()
+        self.debug_print("Stopping client and cleaning up resources.")
         if self.control_ws:
             self.control_ws.close()
-        if self.data_ws:
-            self.data_ws.close()
+        if self.data_ws_connected:
+            self.data_ws_connected.close()
 
         # Join threads to ensure they finish before exiting
         if self.control_ws_thread:
@@ -288,7 +343,7 @@ class STTWebSocketClient:
                     metadata_json = json.dumps(metadata)
                     metadata_length = len(metadata_json)
                     message = struct.pack('<I', metadata_length) + metadata_json.encode('utf-8') + audio_data
-                    self.data_ws.send(message, opcode=websocket.ABNF.OPCODE_BINARY)
+                    self.data_ws_connected.send(message, opcode=websocket.ABNF.OPCODE_BINARY)
                 except Exception as e:
                     self.debug_print(f"Error sending audio data: {e}")
                     break  # Exit the recording loop
@@ -320,10 +375,10 @@ class STTWebSocketClient:
                     frames_per_buffer=CHUNK,
                     input_device_index=self.input_device_index,
                 )
-                self.debug_print(f"Audio recording initialized successfully at {self.device_sample_rate} Hz")
+                self.debug_print(f"Audio recording initialized successfully at {self.device_sample_rate} Hz, device index {self.input_device_index}")
                 return True
             except Exception as e:
-                self.debug_print(f"Failed to initialize audio stream at {self.device_sample_rate} Hz: {e}")
+                self.debug_print(f"Failed to initialize audio stream at {self.device_sample_rate} Hz, device index {self.input_device_index}: {e}")
                 return False
 
         except Exception as e:
@@ -374,9 +429,7 @@ class STTWebSocketClient:
         self.command_thread.start()
 
     def command_processor(self):
-        # print(f"Starting command processor")
         self.debug_print(f"Starting command processor")
-        #while self.is_running and not self.stop_event.is_set():
         while not self.stop_event.is_set():
             try:
                 command = self.commands.get(timeout=0.1)
@@ -386,14 +439,12 @@ class STTWebSocketClient:
                     self.get_parameter(command['parameter'])
                 elif command['type'] == 'call_method':
                     self.call_method(command['method'], command.get('args'), command.get('kwargs'))
-            except queue.Empty:  # Use queue.Empty instead of Queue.Empty
-                continue  # Queue was empty, just loop again
+            except queue.Empty:
+                continue
             except Exception as e:
                 self.debug_print(f"Error in command processor: {e}")
-            # finally:
-        #print(f"Leaving command processor")
-        self.debug_print(f"Leaving command processor")
 
+        self.debug_print(f"Leaving command processor")
 
     def add_command(self, command):
         self.commands.put(command)
@@ -433,7 +484,6 @@ def main():
             if args.set_param:
                 for param, value in args.set_param:
                     try:
-                        # Attempt to parse the value to the appropriate type
                         if '.' in value:
                             value = float(value)
                         else:
@@ -466,22 +516,12 @@ def main():
                     })
 
             # If command-line parameters were used (like --get-param), wait for them to be processed
-            #print("waiting for client commands empty")
-            #count = 0
             if args.set_param or args.get_param or args.call_method:
-                #while not client.commands.empty():
                 while not client.commands.empty():
-                    # print("x", end="", flush=True)
                     time.sleep(0.1)
-                    # count += 1
-                    # if count > 20: 
-                    #     print("BREAK")
-                    #     break
 
             # Start recording directly if no command-line params were provided
-            # print("Connection established. Recording... (Press Ctrl+C to stop)", file=sys.stderr)
             while client.is_running:
-                # print(".", end="", flush=True)
                 time.sleep(0.1)
 
         else:
@@ -493,3 +533,4 @@ def main():
 
 if __name__ == "__main__":
     main()
+

{realtimestt-0.3.3/server → realtimestt-0.3.5/RealtimeSTT_server}/stt_server.py

@@ -68,7 +68,7 @@ The server will broadcast real-time transcription updates to all connected clien
 
 extended_logging = True
 send_recorded_chunk = False
-log_incoming_chunks = False
+log_incoming_chunks = True
 stt_optimizations = False
 
 
@@ -259,23 +259,23 @@ def on_transcription_start(loop):
     })
     asyncio.run_coroutine_threadsafe(audio_queue.put(message), loop)
 
-def on_realtime_transcription_update(text, loop):
-    # Send real-time transcription updates to the client
-    text = preprocess_text(text)
-    message = json.dumps({
-        'type': 'realtime_update',
-        'text': text
-    })
-    asyncio.run_coroutine_threadsafe(audio_queue.put(message), loop)
-
-def on_recorded_chunk(chunk, loop):
-    if send_recorded_chunk:
-        bytes_b64 = base64.b64encode(chunk.tobytes()).decode('utf-8')
-        message = json.dumps({
-            'type': 'recorded_chunk',
-            'bytes': bytes_b64
-        })
-        asyncio.run_coroutine_threadsafe(audio_queue.put(message), loop)
+# def on_realtime_transcription_update(text, loop):
+#     # Send real-time transcription updates to the client
+#     text = preprocess_text(text)
+#     message = json.dumps({
+#         'type': 'realtime_update',
+#         'text': text
+#     })
+#     asyncio.run_coroutine_threadsafe(audio_queue.put(message), loop)
+
+# def on_recorded_chunk(chunk, loop):
+#     if send_recorded_chunk:
+#         bytes_b64 = base64.b64encode(chunk.tobytes()).decode('utf-8')
+#         message = json.dumps({
+#             'type': 'recorded_chunk',
+#             'bytes': bytes_b64
+#         })
+#         asyncio.run_coroutine_threadsafe(audio_queue.put(message), loop)
 
 # Define the server's arguments
 def parse_arguments():
@@ -346,7 +346,7 @@ def parse_arguments():
     parser.add_argument('--data_port', type=int, default=8012,
                         help='The port number used for the data WebSocket connection. Data connections are used to send audio data and receive transcription updates in real time. Default is port 8012.')
 
-    parser.add_argument('--wake_words', type=str, default="Jarvis",
+    parser.add_argument('--wake_words', type=str, default="",
                         help='Specify the wake word(s) that will trigger the server to start listening. For example, setting this to "Jarvis" will make the system start transcribing when it detects the wake word "Jarvis". Default is "Jarvis".')
 
     parser.add_argument('--wake_words_sensitivity', type=float, default=0.5,
@@ -358,7 +358,7 @@ def parse_arguments():
     parser.add_argument('--wake_word_activation_delay', type=float, default=20,
                         help='The delay in seconds before the wake word detection is activated after the system starts listening. This prevents false positives during the start of a session. Default is 0.5 seconds.')
 
-    parser.add_argument('--wakeword_backend', type=str, default='pvporcupine',
+    parser.add_argument('--wakeword_backend', type=str, default='none',
                         help='The backend used for wake word detection. You can specify different backends such as "default" or any custom implementations depending on your setup. Default is "pvporcupine".')
 
     parser.add_argument('--openwakeword_model_paths', type=str, nargs='*',
@@ -619,7 +619,7 @@ async def main_async():
         'on_wakeword_detection_start': make_callback(loop, on_wakeword_detection_start),
         'on_wakeword_detection_end': make_callback(loop, on_wakeword_detection_end),
         'on_transcription_start': make_callback(loop, on_transcription_start),
-        'on_recorded_chunk': make_callback(loop, on_recorded_chunk),
+        # 'on_recorded_chunk': make_callback(loop, on_recorded_chunk),
         'no_log_file': True,  # Disable logging to file
         'use_extended_logging': args.use_extended_logging,
     }

{realtimestt-0.3.3 → realtimestt-0.3.5}/setup.py

@@ -1,34 +1,34 @@
-import setuptools
-
-with open("README.md", "r") as fh:
-    long_description = fh.read()
-
-# Read requirements.txt
-with open('requirements.txt') as f:
-    requirements = f.read().splitlines()
-
-setuptools.setup(
-    name="RealtimeSTT",
-    version="0.3.3",
-    author="Kolja Beigel",
-    author_email="kolja.beigel@web.de",
-    description="A fast Voice Activity Detection and Transcription System",
-    long_description=long_description,
-    long_description_content_type="text/markdown",
-    url="https://github.com/KoljaB/RealTimeSTT",
-    packages=setuptools.find_packages(),
-    classifiers=[
-        "Programming Language :: Python :: 3",
-        "License :: OSI Approved :: MIT License",
-        "Operating System :: OS Independent",
-    ],
-    python_requires='>=3.6',
-    install_requires=requirements,
-    keywords="real-time, audio, transcription, speech-to-text, voice-activity-detection, VAD, real-time-transcription, ambient-noise-detection, microphone-input, faster_whisper, speech-recognition, voice-assistants, audio-processing, buffered-transcription, pyaudio, ambient-noise-level, voice-deactivity",
-    entry_points={
-        'console_scripts': [
-            'stt-server=server.stt_server:main',
-            'stt=server.stt_cli_client:main',
-        ],
-    },
-)
+import setuptools
+
+with open("README.md", "r") as fh:
+    long_description = fh.read()
+
+# Read requirements.txt
+with open('requirements.txt') as f:
+    requirements = f.read().splitlines()
+
+setuptools.setup(
+    name="RealtimeSTT",
+    version="0.3.5",
+    author="Kolja Beigel",
+    author_email="kolja.beigel@web.de",
+    description="A fast Voice Activity Detection and Transcription System",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    url="https://github.com/KoljaB/RealTimeSTT",
+    packages=setuptools.find_packages(include=["RealtimeSTT", "RealtimeSTT_server"]),
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+    ],
+    python_requires='>=3.6',
+    install_requires=requirements,
+    keywords="real-time, audio, transcription, speech-to-text, voice-activity-detection, VAD, real-time-transcription, ambient-noise-detection, microphone-input, faster_whisper, speech-recognition, voice-assistants, audio-processing, buffered-transcription, pyaudio, ambient-noise-level, voice-deactivity",
+    entry_points={
+        'console_scripts': [
+            'stt-server=RealtimeSTT_server.stt_server:main',
+            'stt=RealtimeSTT_server.stt_cli_client:main',
+        ],
+    },
+)