RealTimeSTT 0.3.81__tar.gz → 0.3.91__tar.gz

{RealtimeSTT-0.3.81 → realtimestt-0.3.91}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RealtimeSTT
-Version: 0.3.81
+Version: 0.3.91
 Summary: A fast Voice Activity Detection and Transcription System
 Home-page: https://github.com/KoljaB/RealTimeSTT
 Author: Kolja Beigel
@@ -12,6 +12,18 @@ 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: openwakeword>=0.4.0
+Requires-Dist: websockets==v12.0
+Requires-Dist: websocket-client==1.8.0
+Requires-Dist: numpy<2.0.0
 
 # RealtimeSTT
 [![PyPI](https://img.shields.io/pypi/v/RealtimeSTT)](https://pypi.org/project/RealtimeSTT/)
@@ -43,7 +55,7 @@ https://github.com/user-attachments/assets/797e6552-27cd-41b1-a7f3-e5cbc72094f5
 
 ### Updates
 
-Latest Version: v0.3.8
+Latest Version: v0.3.9
 
 See [release history](https://github.com/KoljaB/RealtimeSTT/releases).
 
@@ -117,10 +129,25 @@ pip install RealtimeSTT
 
 This will install all the necessary dependencies, including a **CPU support only** version of PyTorch.
 
-Although it is possible to run RealtimeSTT with a CPU installation only (use a small model like "tiny" or "base" in this case) you will get way better experience using:
+Although it is possible to run RealtimeSTT with a CPU installation only (use a small model like "tiny" or "base" in this case) you will get way better experience using CUDA (please scroll down).
 
-### GPU Support with CUDA (recommended)
+### Linux Installation
+
+Before installing RealtimeSTT please execute:
 
+```bash
+sudo apt-get install portaudio19-dev
+```
+
+### MacOS Installation
+
+Before installing RealtimeSTT please execute:
+
+```bash
+brew install portaudio
+```
+
+### GPU Support with CUDA (recommended)
 
 ### Updating PyTorch for CUDA Support
 
@@ -450,6 +477,8 @@ When you initialize the `AudioToTextRecorder` class, you have various options to
 
 - **level** (int, default=logging.WARNING): Logging level.
 
+- **batch_size** (int, default=16): Batch size for the main transcription. Set to 0 to deactivate.
+
 - **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.
@@ -489,6 +518,8 @@ When you initialize the `AudioToTextRecorder` class, you have various options to
 
 - **on_realtime_transcription_stabilized**: A callback function that is triggered whenever there's an update in the real-time transcription and returns a higher quality, stabilized text as its argument.
 
+- **realtime_batch_size**: (int, default=16): Batch size for the real-time transcription model. Set to 0 to deactivate.
+
 - **beam_size_realtime** (int, default=3): The beam size to use for real-time transcription beam search decoding.
 
 #### Voice Activation Parameters

{RealtimeSTT-0.3.81 → realtimestt-0.3.91}/README.md

@@ -28,7 +28,7 @@ https://github.com/user-attachments/assets/797e6552-27cd-41b1-a7f3-e5cbc72094f5
 
 ### Updates
 
-Latest Version: v0.3.8
+Latest Version: v0.3.9
 
 See [release history](https://github.com/KoljaB/RealtimeSTT/releases).
 
@@ -102,10 +102,25 @@ pip install RealtimeSTT
 
 This will install all the necessary dependencies, including a **CPU support only** version of PyTorch.
 
-Although it is possible to run RealtimeSTT with a CPU installation only (use a small model like "tiny" or "base" in this case) you will get way better experience using:
+Although it is possible to run RealtimeSTT with a CPU installation only (use a small model like "tiny" or "base" in this case) you will get way better experience using CUDA (please scroll down).
 
-### GPU Support with CUDA (recommended)
+### Linux Installation
+
+Before installing RealtimeSTT please execute:
 
+```bash
+sudo apt-get install portaudio19-dev
+```
+
+### MacOS Installation
+
+Before installing RealtimeSTT please execute:
+
+```bash
+brew install portaudio
+```
+
+### GPU Support with CUDA (recommended)
 
 ### Updating PyTorch for CUDA Support
 
@@ -435,6 +450,8 @@ When you initialize the `AudioToTextRecorder` class, you have various options to
 
 - **level** (int, default=logging.WARNING): Logging level.
 
+- **batch_size** (int, default=16): Batch size for the main transcription. Set to 0 to deactivate.
+
 - **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.
@@ -474,6 +491,8 @@ When you initialize the `AudioToTextRecorder` class, you have various options to
 
 - **on_realtime_transcription_stabilized**: A callback function that is triggered whenever there's an update in the real-time transcription and returns a higher quality, stabilized text as its argument.
 
+- **realtime_batch_size**: (int, default=16): Batch size for the real-time transcription model. Set to 0 to deactivate.
+
 - **beam_size_realtime** (int, default=3): The beam size to use for real-time transcription beam search decoding.
 
 #### Voice Activation Parameters

{RealtimeSTT-0.3.81 → realtimestt-0.3.91}/RealtimeSTT/audio_recorder.py

@@ -34,6 +34,7 @@ from openwakeword.model import Model
 from scipy.signal import resample
 from scipy import signal
 import signal as system_signal
+from faster_whisper import WhisperModel, BatchedInferencePipeline
 import faster_whisper
 import openwakeword
 import collections
@@ -87,11 +88,12 @@ if platform.system() != 'Darwin':
 
 
 class TranscriptionWorker:
-    def __init__(self, conn, stdout_pipe, model_path, compute_type, gpu_device_index, device,
-                 ready_event, shutdown_event, interrupt_stop_event, beam_size, initial_prompt, suppress_tokens):
+    def __init__(self, conn, stdout_pipe, model_path, download_root, compute_type, gpu_device_index, device,
+                 ready_event, shutdown_event, interrupt_stop_event, beam_size, initial_prompt, suppress_tokens, batch_size):
         self.conn = conn
         self.stdout_pipe = stdout_pipe
         self.model_path = model_path
+        self.download_root = download_root
         self.compute_type = compute_type
         self.gpu_device_index = gpu_device_index
         self.device = device
@@ -101,6 +103,7 @@ class TranscriptionWorker:
         self.beam_size = beam_size
         self.initial_prompt = initial_prompt
         self.suppress_tokens = suppress_tokens
+        self.batch_size = batch_size
         self.queue = queue.Queue()
 
     def custom_print(self, *args, **kwargs):
@@ -134,7 +137,10 @@ class TranscriptionWorker:
                 device=self.device,
                 compute_type=self.compute_type,
                 device_index=self.gpu_device_index,
+                download_root=self.download_root,
             )
+            if self.batch_size > 0:
+                model = BatchedInferencePipeline(model=model)
         except Exception as e:
             logging.exception(f"Error initializing main faster_whisper transcription model: {e}")
             raise
@@ -151,13 +157,24 @@ class TranscriptionWorker:
                 try:
                     audio, language = self.queue.get(timeout=0.1)
                     try:
-                        segments, info = model.transcribe(
-                            audio,
-                            language=language if language else None,
-                            beam_size=self.beam_size,
-                            initial_prompt=self.initial_prompt,
-                            suppress_tokens=self.suppress_tokens
-                        )
+                        if self.batch_size > 0:
+                            segments, info = model.transcribe(
+                                audio,
+                                language=language if language else None,
+                                beam_size=self.beam_size,
+                                initial_prompt=self.initial_prompt,
+                                suppress_tokens=self.suppress_tokens,
+                                batch_size=self.batch_size
+                            )
+                        else:
+                            segments, info = model.transcribe(
+                                audio,
+                                language=language if language else None,
+                                beam_size=self.beam_size,
+                                initial_prompt=self.initial_prompt,
+                                suppress_tokens=self.suppress_tokens
+                            )
+
                         transcription = " ".join(seg.text for seg in segments).strip()
                         logging.debug(f"Final text detected with main model: {transcription}")
                         self.conn.send(('success', (transcription, info)))
@@ -195,6 +212,7 @@ class AudioToTextRecorder:
 
     def __init__(self,
                  model: str = INIT_MODEL_TRANSCRIPTION,
+                 download_root: str = None, 
                  language: str = "",
                  compute_type: str = "default",
                  input_device_index: int = None,
@@ -208,6 +226,7 @@ class AudioToTextRecorder:
                  use_microphone=True,
                  spinner=True,
                  level=logging.WARNING,
+                 batch_size: int = 16,
 
                  # Realtime transcription parameters
                  enable_realtime_transcription=False,
@@ -217,6 +236,7 @@ class AudioToTextRecorder:
                  init_realtime_after_seconds=INIT_REALTIME_INITIAL_PAUSE,
                  on_realtime_transcription_update=None,
                  on_realtime_transcription_stabilized=None,
+                 realtime_batch_size: int = 16,
 
                  # Voice activation parameters
                  silero_sensitivity: float = INIT_SILERO_SENSITIVITY,
@@ -280,6 +300,8 @@ class AudioToTextRecorder:
                 'large-v2'.
                 If a specific size is provided, the model is downloaded
                 from the Hugging Face Hub.
+        - download_root (str, default=None): Specifies the root path were the Whisper models 
+          are downloaded to. When empty, the default is used. 
         - language (str, default=""): Language code for speech-to-text engine.
             If not specified, the model will attempt to detect the language
             automatically.
@@ -314,6 +336,7 @@ class AudioToTextRecorder:
         - spinner (bool, default=True): Show spinner animation with current
             state.
         - level (int, default=logging.WARNING): Logging level.
+        - batch_size (int, default=16): Batch size for the main transcription
         - enable_realtime_transcription (bool, default=False): Enables or
             disables real-time transcription of audio. When set to True, the
             audio will be transcribed continuously as it is being recorded.
@@ -345,6 +368,8 @@ class AudioToTextRecorder:
             triggered when the transcribed text stabilizes in quality. The
             stabilized text is generally more accurate but may arrive with a
             slight delay compared to the regular real-time updates.
+        - realtime_batch_size (int, default=16): Batch size for the real-time
+            transcription model.
         - silero_sensitivity (float, default=SILERO_SENSITIVITY): Sensitivity
             for the Silero Voice Activity Detection model ranging from 0
             (least sensitive) to 1 (most sensitive). Default is 0.5.
@@ -508,6 +533,7 @@ class AudioToTextRecorder:
         self.enable_realtime_transcription = enable_realtime_transcription
         self.use_main_model_for_realtime = use_main_model_for_realtime
         self.main_model_type = model
+        self.download_root = download_root
         self.realtime_model_type = realtime_model_type
         self.realtime_processing_pause = realtime_processing_pause
         self.init_realtime_after_seconds = init_realtime_after_seconds
@@ -522,6 +548,8 @@ class AudioToTextRecorder:
         self.beam_size = beam_size
         self.beam_size_realtime = beam_size_realtime
         self.allowed_latency_limit = allowed_latency_limit
+        self.batch_size = batch_size
+        self.realtime_batch_size = realtime_batch_size
 
         self.level = level
         self.audio_queue = mp.Queue()
@@ -630,7 +658,8 @@ class AudioToTextRecorder:
             args=(
                 child_transcription_pipe,
                 child_stdout_pipe,
-                model,
+                self.main_model_type,
+                self.download_root,
                 self.compute_type,
                 self.gpu_device_index,
                 self.device,
@@ -639,7 +668,8 @@ class AudioToTextRecorder:
                 self.interrupt_stop_event,
                 self.beam_size,
                 self.initial_prompt,
-                self.suppress_tokens
+                self.suppress_tokens,
+                self.batch_size
             )
         )
 
@@ -673,8 +703,11 @@ class AudioToTextRecorder:
                     model_size_or_path=self.realtime_model_type,
                     device=self.device,
                     compute_type=self.compute_type,
-                    device_index=self.gpu_device_index
+                    device_index=self.gpu_device_index,
+                    download_root=self.download_root,
                 )
+                if self.realtime_batch_size > 0:
+                    self.realtime_model_type = BatchedInferencePipeline(model=self.realtime_model_type)
 
             except Exception as e:
                 logging.exception("Error initializing faster_whisper "
@@ -2066,13 +2099,23 @@ class AudioToTextRecorder:
                                 continue
                     else:
                         # Perform transcription and assemble the text
-                        segments, info = self.realtime_model_type.transcribe(
-                            audio_array,
-                            language=self.language if self.language else None,
-                            beam_size=self.beam_size_realtime,
-                            initial_prompt=self.initial_prompt,
-                            suppress_tokens=self.suppress_tokens,
-                        )
+                        if self.realtime_batch_size > 0:
+                            segments, info = self.realtime_model_type.transcribe(
+                                audio_array,
+                                language=self.language if self.language else None,
+                                beam_size=self.beam_size_realtime,
+                                initial_prompt=self.initial_prompt,
+                                suppress_tokens=self.suppress_tokens,
+                                batch_size=self.realtime_batch_size
+                            )
+                        else:
+                            segments, info = self.realtime_model_type.transcribe(
+                                audio_array,
+                                language=self.language if self.language else None,
+                                beam_size=self.beam_size_realtime,
+                                initial_prompt=self.initial_prompt,
+                                suppress_tokens=self.suppress_tokens
+                            )
 
                         self.detected_realtime_language = info.language if info.language_probability > 0 else None
                         self.detected_realtime_language_probability = info.language_probability

{RealtimeSTT-0.3.81 → realtimestt-0.3.91}/RealtimeSTT.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RealtimeSTT
-Version: 0.3.81
+Version: 0.3.91
 Summary: A fast Voice Activity Detection and Transcription System
 Home-page: https://github.com/KoljaB/RealTimeSTT
 Author: Kolja Beigel
@@ -12,6 +12,18 @@ 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: openwakeword>=0.4.0
+Requires-Dist: websockets==v12.0
+Requires-Dist: websocket-client==1.8.0
+Requires-Dist: numpy<2.0.0
 
 # RealtimeSTT
 [![PyPI](https://img.shields.io/pypi/v/RealtimeSTT)](https://pypi.org/project/RealtimeSTT/)
@@ -43,7 +55,7 @@ https://github.com/user-attachments/assets/797e6552-27cd-41b1-a7f3-e5cbc72094f5
 
 ### Updates
 
-Latest Version: v0.3.8
+Latest Version: v0.3.9
 
 See [release history](https://github.com/KoljaB/RealtimeSTT/releases).
 
@@ -117,10 +129,25 @@ pip install RealtimeSTT
 
 This will install all the necessary dependencies, including a **CPU support only** version of PyTorch.
 
-Although it is possible to run RealtimeSTT with a CPU installation only (use a small model like "tiny" or "base" in this case) you will get way better experience using:
+Although it is possible to run RealtimeSTT with a CPU installation only (use a small model like "tiny" or "base" in this case) you will get way better experience using CUDA (please scroll down).
 
-### GPU Support with CUDA (recommended)
+### Linux Installation
+
+Before installing RealtimeSTT please execute:
 
+```bash
+sudo apt-get install portaudio19-dev
+```
+
+### MacOS Installation
+
+Before installing RealtimeSTT please execute:
+
+```bash
+brew install portaudio
+```
+
+### GPU Support with CUDA (recommended)
 
 ### Updating PyTorch for CUDA Support
 
@@ -450,6 +477,8 @@ When you initialize the `AudioToTextRecorder` class, you have various options to
 
 - **level** (int, default=logging.WARNING): Logging level.
 
+- **batch_size** (int, default=16): Batch size for the main transcription. Set to 0 to deactivate.
+
 - **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.
@@ -489,6 +518,8 @@ When you initialize the `AudioToTextRecorder` class, you have various options to
 
 - **on_realtime_transcription_stabilized**: A callback function that is triggered whenever there's an update in the real-time transcription and returns a higher quality, stabilized text as its argument.
 
+- **realtime_batch_size**: (int, default=16): Batch size for the real-time transcription model. Set to 0 to deactivate.
+
 - **beam_size_realtime** (int, default=3): The beam size to use for real-time transcription beam search decoding.
 
 #### Voice Activation Parameters

{RealtimeSTT-0.3.81 → realtimestt-0.3.91}/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="0.3.81",
-    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',
-        ],
-    },
-)
+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="0.3.91",
+    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',
+        ],
+    },
+)