RealTimeSTT 0.3.6__tar.gz → 0.3.8__tar.gz

{realtimestt-0.3.6 → RealtimeSTT-0.3.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RealtimeSTT
-Version: 0.3.6
+Version: 0.3.8
 Summary: A fast Voice Activity Detection and Transcription System
 Home-page: https://github.com/KoljaB/RealTimeSTT
 Author: Kolja Beigel
@@ -12,18 +12,6 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: PyAudio==0.2.14
-Requires-Dist: faster-whisper==1.0.3
-Requires-Dist: pvporcupine==1.9.5
-Requires-Dist: webrtcvad-wheels==2.0.14
-Requires-Dist: halo==0.0.31
-Requires-Dist: torch
-Requires-Dist: torchaudio
-Requires-Dist: scipy==1.14.1
-Requires-Dist: websockets==v12.0
-Requires-Dist: websocket-client==1.8.0
-Requires-Dist: openwakeword>=0.4.0
-Requires-Dist: numpy<2.0.0
 
 # RealtimeSTT
 [![PyPI](https://img.shields.io/pypi/v/RealtimeSTT)](https://pypi.org/project/RealtimeSTT/)
@@ -55,7 +43,7 @@ https://github.com/user-attachments/assets/797e6552-27cd-41b1-a7f3-e5cbc72094f5
 
 ### Updates
 
-Latest Version: v0.3.6
+Latest Version: v0.3.8
 
 See [release history](https://github.com/KoljaB/RealtimeSTT/releases).
 
@@ -462,6 +450,8 @@ When you initialize the `AudioToTextRecorder` class, you have various options to
 
 - **level** (int, default=logging.WARNING): Logging level.
 
+- **init_logging** (bool, default=True): Whether to initialize the logging framework. Set to False to manage this yourself.
+
 - **handle_buffer_overflow** (bool, default=True): If set, the system will log a warning when an input overflow occurs during recording and remove the data from the buffer.
 
 - **beam_size** (int, default=5): The beam size to use for beam search decoding.

{realtimestt-0.3.6 → RealtimeSTT-0.3.8}/README.md

@@ -28,7 +28,7 @@ https://github.com/user-attachments/assets/797e6552-27cd-41b1-a7f3-e5cbc72094f5
 
 ### Updates
 
-Latest Version: v0.3.6
+Latest Version: v0.3.8
 
 See [release history](https://github.com/KoljaB/RealtimeSTT/releases).
 
@@ -435,6 +435,8 @@ When you initialize the `AudioToTextRecorder` class, you have various options to
 
 - **level** (int, default=logging.WARNING): Logging level.
 
+- **init_logging** (bool, default=True): Whether to initialize the logging framework. Set to False to manage this yourself.
+
 - **handle_buffer_overflow** (bool, default=True): If set, the system will log a warning when an input overflow occurs during recording and remove the data from the buffer.
 
 - **beam_size** (int, default=5): The beam size to use for beam search decoding.

RealtimeSTT-0.3.8/RealtimeSTT/__init__.py

@@ -0,0 +1,3 @@
+from .audio_recorder import AudioToTextRecorder
+from .audio_recorder_client import AudioToTextRecorderClient
+from .audio_input import AudioInput

RealtimeSTT-0.3.8/RealtimeSTT/audio_input.py

@@ -0,0 +1,153 @@
+from colorama import init, Fore, Style
+import pyaudio
+import logging
+import time
+
+
+class AudioInput:
+    def __init__(self, input_device_index=None, debug_mode=False):
+        self.input_device_index = input_device_index
+        self.debug_mode = debug_mode
+        self.audio_interface = None
+        self.stream = None
+        self.device_sample_rate = None
+
+        # PyAudio constants
+        self.CHUNK = 1024
+        self.FORMAT = pyaudio.paInt16  
+        self.CHANNELS = 1
+        self.DESIRED_RATE = 16000
+
+    def get_supported_sample_rates(self, device_index):
+        """Test which standard sample rates are supported by the specified device."""
+        standard_rates = [8000, 9600, 11025, 12000, 16000, 22050, 24000, 32000, 44100, 48000]
+        supported_rates = []
+
+        device_info = self.audio_interface.get_device_info_by_index(device_index)
+        max_channels = device_info.get('maxInputChannels')  # Changed from maxOutputChannels
+
+        for rate in standard_rates:
+            try:
+                if self.audio_interface.is_format_supported(
+                    rate,
+                    input_device=device_index,  # Changed to input_device
+                    input_channels=max_channels,  # Changed to input_channels 
+                    input_format=self.FORMAT,  # Changed to input_format
+                ):
+                    supported_rates.append(rate)
+            except:
+                continue
+        return supported_rates
+
+    def _get_best_sample_rate(self, actual_device_index, desired_rate):
+        """Determines the best available sample rate for the device."""
+        try:
+            device_info = self.audio_interface.get_device_info_by_index(actual_device_index)
+            supported_rates = self.get_supported_sample_rates(actual_device_index)
+
+            if desired_rate in supported_rates:
+                return desired_rate
+
+            return max(supported_rates)
+
+            # lower_rates = [r for r in supported_rates if r <= desired_rate]
+            # if lower_rates:
+            #     return max(lower_rates)
+
+            # higher_rates = [r for r in supported_rates if r > desired_rate]
+            # if higher_rates:
+            #     return min(higher_rates)
+
+            return int(device_info.get('defaultSampleRate', 44100))
+
+        except Exception as e:
+            logging.warning(f"Error determining sample rate: {e}")
+            return 44100  # Safe fallback
+
+    def list_devices(self):
+        """List all available audio input devices with supported sample rates."""
+        try:
+            init()  # Initialize colorama
+            self.audio_interface = pyaudio.PyAudio()
+            device_count = self.audio_interface.get_device_count()
+
+            print(f"Available audio input devices:")
+            #print(f"{Fore.LIGHTBLUE_EX}Available audio input devices:{Style.RESET_ALL}")
+            for i in range(device_count):
+                device_info = self.audio_interface.get_device_info_by_index(i)
+                device_name = device_info.get('name')
+                max_input_channels = device_info.get('maxInputChannels', 0)
+
+                if max_input_channels > 0:  # Only consider devices with input capabilities
+                    supported_rates = self.get_supported_sample_rates(i)
+                    print(f"{Fore.LIGHTGREEN_EX}Device {Style.RESET_ALL}{i}{Fore.LIGHTGREEN_EX}: {device_name}{Style.RESET_ALL}")
+                    
+                    # Format each rate in cyan
+                    if supported_rates:
+                        rates_formatted = ", ".join([f"{Fore.CYAN}{rate}{Style.RESET_ALL}" for rate in supported_rates])
+                        print(f"  {Fore.YELLOW}Supported sample rates: {rates_formatted}{Style.RESET_ALL}")
+                    else:
+                        print(f"  {Fore.YELLOW}Supported sample rates: None{Style.RESET_ALL}")
+
+        except Exception as e:
+            print(f"Error listing devices: {e}")
+        finally:
+            if self.audio_interface:
+                self.audio_interface.terminate()
+
+    def setup(self):
+        """Initialize audio interface and open stream"""
+        try:
+            self.audio_interface = pyaudio.PyAudio()
+
+            if self.debug_mode:
+                print(f"Input device index: {self.input_device_index}")
+            actual_device_index = (self.input_device_index if self.input_device_index is not None 
+                                else self.audio_interface.get_default_input_device_info()['index'])
+            
+            if self.debug_mode:
+                print(f"Actual selected device index: {actual_device_index}")
+            self.input_device_index = actual_device_index
+            self.device_sample_rate = self._get_best_sample_rate(actual_device_index, self.DESIRED_RATE)
+
+            if self.debug_mode:
+                print(f"Setting up audio on device {self.input_device_index} with sample rate {self.device_sample_rate}")
+
+            try:
+                self.stream = self.audio_interface.open(
+                    format=self.FORMAT,
+                    channels=self.CHANNELS,
+                    rate=self.device_sample_rate,
+                    input=True,
+                    frames_per_buffer=self.CHUNK,
+                    input_device_index=self.input_device_index,
+                )
+                if self.debug_mode:
+                    print(f"Audio recording initialized successfully at {self.device_sample_rate} Hz")
+                return True
+            except Exception as e:
+                print(f"Failed to initialize audio stream at {self.device_sample_rate} Hz: {e}")
+                return False
+
+        except Exception as e:
+            print(f"Error initializing audio recording: {e}")
+            if self.audio_interface:
+                self.audio_interface.terminate()
+            return False
+
+    def read_chunk(self):
+        """Read a chunk of audio data"""
+        return self.stream.read(self.CHUNK, exception_on_overflow=False)
+
+    def cleanup(self):
+        """Clean up audio resources"""
+        try:
+            if self.stream:
+                self.stream.stop_stream()
+                self.stream.close()
+                self.stream = None
+            if self.audio_interface:
+                self.audio_interface.terminate()
+                self.audio_interface = None
+        except Exception as e:
+            print(f"Error cleaning up audio resources: {e}")

{realtimestt-0.3.6 → RealtimeSTT-0.3.8}/RealtimeSTT/audio_recorder_client.py

@@ -9,15 +9,18 @@ import websocket
 import threading
 import platform
 import logging
-import pyaudio
 import socket
 import struct
 import signal
+import wave
 import json
 import time
 import sys
 import os
 
+# Import the AudioInput class
+from .audio_input import AudioInput
+
 DEFAULT_CONTROL_URL = "ws://127.0.0.1:8011"
 DEFAULT_DATA_URL = "ws://127.0.0.1:8012"
 
@@ -36,11 +39,8 @@ INIT_WAKE_WORD_TIMEOUT = 5.0
 INIT_WAKE_WORD_BUFFER_DURATION = 0.1
 ALLOWED_LATENCY_LIMIT = 100
 
-CHUNK = 1024
-FORMAT = pyaudio.paInt16
-CHANNELS = 1
-SAMPLE_RATE = 16000
 BUFFER_SIZE = 512
+SAMPLE_RATE = 16000
 
 INIT_HANDLE_BUFFER_OVERFLOW = False
 if platform.system() != 'Darwin':
@@ -143,6 +143,7 @@ class AudioToTextRecorderClient:
                  control_url: str = DEFAULT_CONTROL_URL,
                  data_url: str = DEFAULT_DATA_URL,
                  autostart_server: bool = True,
+                 output_wav_file: str = None,
                  ):
 
         # Set instance variables from constructor parameters
@@ -213,6 +214,7 @@ class AudioToTextRecorderClient:
         self.control_url = control_url
         self.data_url = data_url
         self.autostart_server = autostart_server
+        self.output_wav_file = output_wav_file
 
         # Instance variables
         self.muted = False
@@ -223,6 +225,9 @@ class AudioToTextRecorderClient:
         self.final_text_ready = threading.Event()
         self.realtime_text = ""
         self.final_text = ""
+        self._recording = False
+        self.server_already_running = False
+        self.wav_file = None
 
         self.request_counter = 0
         self.pending_requests = {}  # Map from request_id to threading.Event and value
@@ -238,6 +243,13 @@ class AudioToTextRecorderClient:
         if self.use_microphone:
             self.start_recording()
 
+
+        if self.server_already_running:
+            self.set_parameter("language", self.language)
+            # self.set_parameter("model", self.model)
+
+
+
     def text(self, on_transcription_finished=None):
         self.realtime_text = ""
         self.submitted_realtime_text = ""
@@ -251,17 +263,15 @@ class AudioToTextRecorderClient:
             wait_interval = 0.02  # Wait in small intervals, e.g., 100ms
             max_wait_time = 60  # Timeout after 60 seconds
 
-            while total_wait_time < max_wait_time:
+            while total_wait_time < max_wait_time and self.is_running and self._recording:
                 if self.final_text_ready.wait(timeout=wait_interval):
                     break  # Break if transcription is ready
-                
-                # if not self.realtime_text == self.submitted_realtime_text:
-                #     if self.on_realtime_transcription_update:
-                #         self.on_realtime_transcription_update(self.realtime_text)
-                #     self.submitted_realtime_text = self.realtime_text
 
-                total_wait_time += wait_interval
+                if not self.is_running or not self._recording:
+                    break
                 
+                total_wait_time += wait_interval
+
                 # Check if a manual interrupt has occurred
                 if total_wait_time >= max_wait_time:
                     if self.debug_mode:
@@ -273,6 +283,9 @@ class AudioToTextRecorderClient:
 
             self.recording_start.clear()
 
+            if not self.is_running or not self._recording:
+                return ""
+
             if on_transcription_finished:
                 threading.Thread(target=on_transcription_finished, args=(self.final_text,)).start()
 
@@ -280,7 +293,7 @@ class AudioToTextRecorderClient:
 
         except KeyboardInterrupt:
             if self.debug_mode:
-                print("KeyboardInterrupt in record_and_send_audio, exiting...")
+                print("KeyboardInterrupt in text(), exiting...")
             raise KeyboardInterrupt
 
         except Exception as e:
@@ -318,7 +331,7 @@ class AudioToTextRecorderClient:
         if not self.ensure_server_running():
             print("Cannot start STT server. Exiting.")
             return False
-        
+
         try:
             # Connect to control WebSocket
             self.control_ws = websocket.WebSocketApp(self.control_url,
@@ -438,7 +451,7 @@ class AudioToTextRecorderClient:
         if not self.is_server_running():
             if self.debug_mode:
                 print("STT server is not running.", file=sys.stderr)
-            if self.autostart_server or self.ask_to_start_server():
+            if self.autostart_server:
                 self.start_server()
                 if self.debug_mode:
                     print("Waiting for STT server to start...", file=sys.stderr)
@@ -454,7 +467,16 @@ class AudioToTextRecorderClient:
             else:
                 print("STT server is required. Please start it manually.", file=sys.stderr)
                 return False
+        
+        else:
+            self.server_already_running = True
+
         return True
+    
+    def list_devices(self):
+        """List all available audio input devices."""
+        audio = AudioInput(debug_mode=self.debug_mode)
+        audio.list_devices()
 
     def start_recording(self):
         self.recording_thread = threading.Thread(target=self.record_and_send_audio)
@@ -462,45 +484,29 @@ class AudioToTextRecorderClient:
         self.recording_thread.start()
 
     def setup_audio(self):
-        try:
-            self.audio_interface = pyaudio.PyAudio()
-            self.input_device_index = None
-            try:
-                default_device = self.audio_interface.get_default_input_device_info()
-                self.input_device_index = default_device['index']
-            except OSError as e:
-                print(f"No default input device found: {e}")
-                return False
-
-            self.device_sample_rate = 16000  # Try 16000 Hz first
-
-            try:
-                self.stream = self.audio_interface.open(
-                    format=FORMAT,
-                    channels=CHANNELS,
-                    rate=self.device_sample_rate,
-                    input=True,
-                    frames_per_buffer=CHUNK,
-                    input_device_index=self.input_device_index,
-                )
-                if self.debug_mode:
-                    print(f"Audio recording initialized successfully at {self.device_sample_rate} Hz")
-                return True
-            except Exception as e:
-                print(f"Failed to initialize audio stream at {self.device_sample_rate} Hz: {e}")
-                return False
-
-        except Exception as e:
-            print(f"Error initializing audio recording: {e}")
-            if self.audio_interface:
-                self.audio_interface.terminate()
-            return False
+        """Initialize audio input"""
+        self.audio_input = AudioInput(
+            input_device_index=self.input_device_index,
+            debug_mode=self.debug_mode
+        )
+        return self.audio_input.setup()
 
     def record_and_send_audio(self):
+        """Record and stream audio data"""
+        self._recording = True
+
         try:
             if not self.setup_audio():
                 raise Exception("Failed to set up audio recording.")
 
+            # Initialize WAV file writer if output_wav_file is provided
+            if self.output_wav_file:
+                self.wav_file = wave.open(self.output_wav_file, 'wb')
+                self.wav_file.setnchannels(1)
+                self.wav_file.setsampwidth(2)
+                self.wav_file.setframerate(self.audio_input.device_sample_rate)  # Use self.device_sample_rate
+
+
             if self.debug_mode:
                 print("Recording and sending audio...")
 
@@ -510,7 +516,10 @@ class AudioToTextRecorderClient:
                     continue
 
                 try:
-                    audio_data = self.stream.read(CHUNK)
+                    audio_data = self.audio_input.read_chunk()
+
+                    if self.wav_file:
+                        self.wav_file.writeframes(audio_data)
 
                     if self.on_recorded_chunk:
                         self.on_recorded_chunk(audio_data)
@@ -519,7 +528,7 @@ class AudioToTextRecorderClient:
                         continue
 
                     if self.recording_start.is_set():
-                        metadata = {"sampleRate": self.device_sample_rate}
+                        metadata = {"sampleRate": self.audio_input.device_sample_rate}
                         metadata_json = json.dumps(metadata)
                         metadata_length = len(metadata_json)
                         message = struct.pack('<I', metadata_length) + metadata_json.encode('utf-8') + audio_data
@@ -528,30 +537,26 @@ class AudioToTextRecorderClient:
                             if log_outgoing_chunks:
                                 print(".", flush=True, end='')
                             self.data_ws.send(message, opcode=websocket.ABNF.OPCODE_BINARY)
-                except KeyboardInterrupt:  # handle manual interruption (Ctrl+C)
+                except KeyboardInterrupt:
                     if self.debug_mode:
                         print("KeyboardInterrupt in record_and_send_audio, exiting...")
                     break
                 except Exception as e:
                     print(f"Error sending audio data: {e}")
-                    break  # Exit the recording loop
+                    break
 
         except Exception as e:
-            print(f"Error in record_and_send_audio: {e}")
+            print(f"Error in record_and_send_audio: {e}", file=sys.stderr)
         finally:
             self.cleanup_audio()
+            self.final_text_ready.set() # fake final text to stop the text() method
+            self.is_running = False
+            self._recording = False
 
     def cleanup_audio(self):
-        try:
-            if self.stream:
-                self.stream.stop_stream()
-                self.stream.close()
-                self.stream = None
-            if self.audio_interface:
-                self.audio_interface.terminate()
-                self.audio_interface = None
-        except Exception as e:
-            print(f"Error cleaning up audio resources: {e}")
+        """Clean up audio resources"""
+        if hasattr(self, 'audio_input'):
+            self.audio_input.cleanup()
 
     def on_control_message(self, ws, message):
         try:
@@ -585,7 +590,7 @@ class AudioToTextRecorderClient:
                     self.realtime_text = data['text']
 
                     timestamp = datetime.now().strftime('%H:%M:%S.%f')[:-3]
-                    print(f"Realtime text [{timestamp}]: {bcolors.OKCYAN}{self.realtime_text}{bcolors.ENDC}")
+                    # print(f"Realtime text [{timestamp}]: {bcolors.OKCYAN}{self.realtime_text}{bcolors.ENDC}")
 
                     if self.on_realtime_transcription_update:
                         # Call the callback in a new thread to avoid blocking
@@ -704,14 +709,14 @@ class AudioToTextRecorderClient:
         self.control_ws.send(json.dumps(command))
 
     def shutdown(self):
+        """Shutdown all resources"""
         self.is_running = False
-        #self.stop_event.set()
         if self.control_ws:
             self.control_ws.close()
         if self.data_ws:
             self.data_ws.close()
 
-        # Join threads to ensure they finish before exiting
+        # Join threads
         if self.control_ws_thread:
             self.control_ws_thread.join()
         if self.data_ws_thread:
@@ -719,12 +724,8 @@ class AudioToTextRecorderClient:
         if self.recording_thread:
             self.recording_thread.join()
 
-        # Clean up audio resources
-        if self.stream:
-            self.stream.stop_stream()
-            self.stream.close()
-        if self.audio_interface:
-            self.audio_interface.terminate()
+        # Clean up audio
+        self.cleanup_audio()
 
     def __enter__(self):
         """

{realtimestt-0.3.6 → RealtimeSTT-0.3.8}/RealtimeSTT.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RealtimeSTT
-Version: 0.3.6
+Version: 0.3.8
 Summary: A fast Voice Activity Detection and Transcription System
 Home-page: https://github.com/KoljaB/RealTimeSTT
 Author: Kolja Beigel
@@ -12,18 +12,6 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: PyAudio==0.2.14
-Requires-Dist: faster-whisper==1.0.3
-Requires-Dist: pvporcupine==1.9.5
-Requires-Dist: webrtcvad-wheels==2.0.14
-Requires-Dist: halo==0.0.31
-Requires-Dist: torch
-Requires-Dist: torchaudio
-Requires-Dist: scipy==1.14.1
-Requires-Dist: websockets==v12.0
-Requires-Dist: websocket-client==1.8.0
-Requires-Dist: openwakeword>=0.4.0
-Requires-Dist: numpy<2.0.0
 
 # RealtimeSTT
 [![PyPI](https://img.shields.io/pypi/v/RealtimeSTT)](https://pypi.org/project/RealtimeSTT/)
@@ -55,7 +43,7 @@ https://github.com/user-attachments/assets/797e6552-27cd-41b1-a7f3-e5cbc72094f5
 
 ### Updates
 
-Latest Version: v0.3.6
+Latest Version: v0.3.8
 
 See [release history](https://github.com/KoljaB/RealtimeSTT/releases).
 
@@ -462,6 +450,8 @@ When you initialize the `AudioToTextRecorder` class, you have various options to
 
 - **level** (int, default=logging.WARNING): Logging level.
 
+- **init_logging** (bool, default=True): Whether to initialize the logging framework. Set to False to manage this yourself.
+
 - **handle_buffer_overflow** (bool, default=True): If set, the system will log a warning when an input overflow occurs during recording and remove the data from the buffer.
 
 - **beam_size** (int, default=5): The beam size to use for beam search decoding.

{realtimestt-0.3.6 → RealtimeSTT-0.3.8}/RealtimeSTT.egg-info/SOURCES.txt

@@ -2,6 +2,7 @@ LICENSE
 README.md
 setup.py
 RealtimeSTT/__init__.py
+RealtimeSTT/audio_input.py
 RealtimeSTT/audio_recorder.py
 RealtimeSTT/audio_recorder_client.py
 RealtimeSTT.egg-info/PKG-INFO

{realtimestt-0.3.6 → RealtimeSTT-0.3.8}/RealtimeSTT.egg-info/requires.txt

@@ -6,6 +6,7 @@ halo==0.0.31
 torch
 torchaudio
 scipy==1.14.1
+websocket==0.2.1
 websockets==v12.0
 websocket-client==1.8.0
 openwakeword>=0.4.0

{realtimestt-0.3.6 → RealtimeSTT-0.3.8}/RealtimeSTT_server/install_packages.py

@@ -53,53 +53,3 @@ def check_and_install_packages(packages):
             else:
                 print(f"The program requires '{install_name}' to run. Exiting...")
                 sys.exit(1)
-
-
-# import subprocess
-# import sys
-
-# def check_and_install_packages(packages):
-#     """
-#     Checks if the specified packages are installed, and if not, prompts the user
-#     to install them.
-
-#     Parameters:
-#     - packages: A list of dictionaries, each containing:
-#         - 'import_name': The name used in the import statement.
-#         - 'install_name': (Optional) The name used in the pip install command.
-#                           Defaults to 'import_name' if not provided.
-#         - 'version': (Optional) Version constraint for the package.
-#     """
-#     for package in packages:
-#         import_name = package['import_name']
-#         install_name = package.get('install_name', import_name)
-#         version = package.get('version', '')
-
-#         try:
-#             print(f"import {import_name}")
-#             __import__(import_name)
-#             print(f"imported {import_name}")
-#         except ImportError:
-#             user_input = input(
-#                 f"This program requires the '{import_name}' library, which is not installed.\n"
-#                 f"Do you want to install it now? (y/n): "
-#             )
-#             if user_input.strip().lower() == 'y':
-#                 try:
-#                     # Build the pip install command
-#                     install_command = [sys.executable, "-m", "pip", "install"]
-#                     if version:
-#                         install_command.append(f"{install_name}{version}")
-#                     else:
-#                         install_command.append(install_name)
-
-#                     subprocess.check_call(install_command)
-#                     __import__(import_name)
-#                     print(f"Successfully installed '{install_name}'.")
-#                 except Exception as e:
-#                     print(f"An error occurred while installing '{install_name}': {e}")
-#                     sys.exit(1)
-#             else:
-#                 print(f"The program requires the '{import_name}' library to run. Exiting...")
-#                 sys.exit(1)
-