whisperpipe 0.1.0__tar.gz

whisperpipe-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Erfan Ramezani
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

whisperpipe-0.1.0/PKG-INFO

@@ -0,0 +1,229 @@
+Metadata-Version: 2.4
+Name: whisperpipe
+Version: 0.1.0
+Summary: Real-time speech-to-text streaming with OpenAI Whisper
+License: MIT
+License-File: LICENSE
+Keywords: whisper,openai,speech-to-text,stt,asr,automatic speech recognition,real-time,realtime,audio,microphone,transcription,streaming,live transcription
+Author: Erfan Ramezani
+Author-email: erfanramezany245@gmail.com
+Requires-Python: >=3.9,<3.13
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: End Users/Desktop
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Environment :: Console
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Classifier: Topic :: Multimedia :: Sound/Audio :: Capture/Recording
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Dist: openai-whisper (>=20240930)
+Requires-Dist: pyaudio (>=0.2.14)
+Requires-Dist: pynput (>=1.7.7)
+Requires-Dist: sounddevice (>=0.5.2)
+Project-URL: Bug Tracker, https://github.com/Erfan-ram/whisperpipe/issues
+Project-URL: Changelog, https://github.com/Erfan-ram/whisperpipe/releases
+Project-URL: Documentation, https://github.com/Erfan-ram/whisperpipe/blob/main/README.md
+Project-URL: Homepage, https://github.com/Erfan-ram/whisperpipe
+Project-URL: Repository, https://github.com/Erfan-ram/whisperpipe
+Project-URL: Source, https://github.com/Erfan-ram/whisperpipe
+Description-Content-Type: text/markdown
+
+# whisperpipe
+
+Real-time speech-to-text streaming with OpenAI Whisper
+
+## Description
+
+whisperpipe is a powerful, easy-to-use Python package for real-time, offline audio transcription using OpenAI's Whisper model. It runs locally, making it a free and private solution for continuous speech-to-text applications. It provides seamless integration with callback functions for LLM processing and supports pause/resume functionality for interactive applications.
+
+## Why whisperpipe?
+
+In a world where most ASR (Automatic Speech Recognition) services are cloud-based, whisperpipe offers a refreshing alternative by harnessing the power of OpenAI's Whisper model to run directly on your local machine. This approach provides several key advantages:
+
+- **Complete Privacy**: Since all transcription is done locally, your voice data never leaves your computer. This is crucial for applications that handle sensitive or private conversations.
+- **Zero Cost**: Say goodbye to recurring subscription fees and per-minute charges. whisperpipe is free to use, making it an economical choice for both hobbyists and commercial projects.
+- **No Internet Required**: Whether you're on a plane, in a remote location, or simply have an unstable internet connection, whisperpipe works flawlessly offline.
+- **Real-time Performance**: Designed for continuous, real-time transcription, whisperpipe is ideal for live applications such as voice-controlled assistants, dictation software, and more.
+- **Unleash the Power of Whisper**: By running the Whisper model locally, you have full control over the transcription process, from model selection to performance tuning.
+
+whisperpipe empowers you to build powerful, private, and cost-effective voice applications with ease.
+
+## Features
+
+- **Real-time audio transcription** using OpenAI Whisper
+- **Callback system** for custom processing (LLM integration, etc.)
+- **Pause/Resume functionality** for interactive applications
+- **Multiple language support**
+- **Configurable processing parameters**
+- **Thread-safe operation**
+- **Easy installation and usage**
+
+## Installation
+
+### From PyPI
+
+```bash
+pip install whisperpipe
+```
+
+### From GitHub
+
+```bash
+pip install git+https://github.com/Erfan-ram/whisperpipe.git
+```
+
+## Quick Start
+
+```python
+from whisperpipe import pipeStream
+
+# Basic usage
+transcriber = pipeStream(
+    model_name="base",
+    language="en",
+    finalization_delay=10.0,
+    processing_interval=1.0
+)
+
+# Start streaming
+transcriber.start_streaming()
+```
+
+## Usage Examples
+
+### Basic Transcription
+
+```python
+from whisperpipe import pipeStream
+
+# Create transcriber instance
+transcriber = pipeStream(
+    model_name="base",
+    language="en",
+    finalization_delay=10.0,
+    processing_interval=1.0
+)
+
+# Start transcription
+transcriber.start_streaming()
+
+# The transcribed text will be printed to console
+# Press Ctrl+C to stop
+```
+
+### With Custom Callback (LLM Integration)
+
+```python
+from whisperpipe import pipeStream
+
+def llm_processor(text):
+    """Custom function to process transcribed text"""
+    print(f"Processing: {text}")
+    # Your LLM integration here
+    # e.g., send to OpenAI, Claude, local model, etc.
+    response = your_llm_api.chat(text)
+    print(f"Response: {response}")
+    return response
+
+# Create transcriber with callback
+transcriber = pipeStream(
+    model_name="base",
+    language="en",
+    finalization_delay=10.0,
+    processing_interval=1.0
+)
+
+# Register callback
+transcriber.set_def_callback(llm_processor)
+
+# Start streaming with LLM integration
+transcriber.start_streaming()
+```
+
+### Interactive Mode with Pause/Resume
+
+```python
+from whisperpipe import pipeStream
+import time
+
+def interactive_processor(text):
+    """Process text and pause for response"""
+    # Pause transcriber while processing
+    transcriber.pause_streaming()
+    
+    print(f"User said: {text}")
+    
+    # Process with your system
+    response = process_with_llm(text)
+    
+    # Speak or display response
+    print(f"Assistant: {response}")
+    
+    # Resume for next input
+    transcriber.resume_streaming()
+
+transcriber = pipeStream()
+transcriber.set_def_callback(interactive_processor)
+transcriber.start_streaming()
+```
+
+## API Reference
+
+### Constructor Parameters
+
+- `model_name` (str): Whisper model name ("tiny", "base", "small", "medium", "large"). Default: "base"
+- `language` (str): Language code for transcription ("en", "es", "fr", etc.). Default: "en"
+- `finalization_delay` (float): Wait time in seconds before finalizing transcription. Default: 10.0
+- `processing_interval` (float): Interval in seconds between processing cycles. Default: 1.0
+- `buffer_duration_seconds` (float): Time window in seconds to hold audio for processing. Default: 5.0
+- `debug_mode` (bool): Enable debug mode for detailed logging. Default: True
+
+### Methods
+
+#### Core Methods
+- `start_streaming()`: Start audio capture and transcription
+- `stop_streaming()`: Stop audio capture and transcription
+
+#### Callback System
+- `set_def_callback(callback_function)`: Register a callback function for processing transcribed text
+- `set_def_callback(None)`: Clear the callback (use default behavior)
+
+#### Pause/Resume Control
+- `pause_streaming()`: Pause audio processing temporarily
+- `resume_streaming()`: Resume audio processing
+- `is_paused()`: Check if transcriber is paused
+- `is_running()`: Check if transcriber is running
+
+## Requirements
+
+- Python 3.8+
+- PyAudio
+- OpenAI Whisper
+- PyTorch
+- NumPy
+- pynput
+
+## License
+
+MIT License
+
+## Author
+
+Erfan Ramezani - erfanramezany245@gmail.com
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.
+
+## Support
+
+For issues and questions, please use the [GitHub Issues](https://github.com/Erfan-ram/whisperpipe/issues) page.

whisperpipe-0.1.0/README.md

@@ -0,0 +1,190 @@
+# whisperpipe
+
+Real-time speech-to-text streaming with OpenAI Whisper
+
+## Description
+
+whisperpipe is a powerful, easy-to-use Python package for real-time, offline audio transcription using OpenAI's Whisper model. It runs locally, making it a free and private solution for continuous speech-to-text applications. It provides seamless integration with callback functions for LLM processing and supports pause/resume functionality for interactive applications.
+
+## Why whisperpipe?
+
+In a world where most ASR (Automatic Speech Recognition) services are cloud-based, whisperpipe offers a refreshing alternative by harnessing the power of OpenAI's Whisper model to run directly on your local machine. This approach provides several key advantages:
+
+- **Complete Privacy**: Since all transcription is done locally, your voice data never leaves your computer. This is crucial for applications that handle sensitive or private conversations.
+- **Zero Cost**: Say goodbye to recurring subscription fees and per-minute charges. whisperpipe is free to use, making it an economical choice for both hobbyists and commercial projects.
+- **No Internet Required**: Whether you're on a plane, in a remote location, or simply have an unstable internet connection, whisperpipe works flawlessly offline.
+- **Real-time Performance**: Designed for continuous, real-time transcription, whisperpipe is ideal for live applications such as voice-controlled assistants, dictation software, and more.
+- **Unleash the Power of Whisper**: By running the Whisper model locally, you have full control over the transcription process, from model selection to performance tuning.
+
+whisperpipe empowers you to build powerful, private, and cost-effective voice applications with ease.
+
+## Features
+
+- **Real-time audio transcription** using OpenAI Whisper
+- **Callback system** for custom processing (LLM integration, etc.)
+- **Pause/Resume functionality** for interactive applications
+- **Multiple language support**
+- **Configurable processing parameters**
+- **Thread-safe operation**
+- **Easy installation and usage**
+
+## Installation
+
+### From PyPI
+
+```bash
+pip install whisperpipe
+```
+
+### From GitHub
+
+```bash
+pip install git+https://github.com/Erfan-ram/whisperpipe.git
+```
+
+## Quick Start
+
+```python
+from whisperpipe import pipeStream
+
+# Basic usage
+transcriber = pipeStream(
+    model_name="base",
+    language="en",
+    finalization_delay=10.0,
+    processing_interval=1.0
+)
+
+# Start streaming
+transcriber.start_streaming()
+```
+
+## Usage Examples
+
+### Basic Transcription
+
+```python
+from whisperpipe import pipeStream
+
+# Create transcriber instance
+transcriber = pipeStream(
+    model_name="base",
+    language="en",
+    finalization_delay=10.0,
+    processing_interval=1.0
+)
+
+# Start transcription
+transcriber.start_streaming()
+
+# The transcribed text will be printed to console
+# Press Ctrl+C to stop
+```
+
+### With Custom Callback (LLM Integration)
+
+```python
+from whisperpipe import pipeStream
+
+def llm_processor(text):
+    """Custom function to process transcribed text"""
+    print(f"Processing: {text}")
+    # Your LLM integration here
+    # e.g., send to OpenAI, Claude, local model, etc.
+    response = your_llm_api.chat(text)
+    print(f"Response: {response}")
+    return response
+
+# Create transcriber with callback
+transcriber = pipeStream(
+    model_name="base",
+    language="en",
+    finalization_delay=10.0,
+    processing_interval=1.0
+)
+
+# Register callback
+transcriber.set_def_callback(llm_processor)
+
+# Start streaming with LLM integration
+transcriber.start_streaming()
+```
+
+### Interactive Mode with Pause/Resume
+
+```python
+from whisperpipe import pipeStream
+import time
+
+def interactive_processor(text):
+    """Process text and pause for response"""
+    # Pause transcriber while processing
+    transcriber.pause_streaming()
+    
+    print(f"User said: {text}")
+    
+    # Process with your system
+    response = process_with_llm(text)
+    
+    # Speak or display response
+    print(f"Assistant: {response}")
+    
+    # Resume for next input
+    transcriber.resume_streaming()
+
+transcriber = pipeStream()
+transcriber.set_def_callback(interactive_processor)
+transcriber.start_streaming()
+```
+
+## API Reference
+
+### Constructor Parameters
+
+- `model_name` (str): Whisper model name ("tiny", "base", "small", "medium", "large"). Default: "base"
+- `language` (str): Language code for transcription ("en", "es", "fr", etc.). Default: "en"
+- `finalization_delay` (float): Wait time in seconds before finalizing transcription. Default: 10.0
+- `processing_interval` (float): Interval in seconds between processing cycles. Default: 1.0
+- `buffer_duration_seconds` (float): Time window in seconds to hold audio for processing. Default: 5.0
+- `debug_mode` (bool): Enable debug mode for detailed logging. Default: True
+
+### Methods
+
+#### Core Methods
+- `start_streaming()`: Start audio capture and transcription
+- `stop_streaming()`: Stop audio capture and transcription
+
+#### Callback System
+- `set_def_callback(callback_function)`: Register a callback function for processing transcribed text
+- `set_def_callback(None)`: Clear the callback (use default behavior)
+
+#### Pause/Resume Control
+- `pause_streaming()`: Pause audio processing temporarily
+- `resume_streaming()`: Resume audio processing
+- `is_paused()`: Check if transcriber is paused
+- `is_running()`: Check if transcriber is running
+
+## Requirements
+
+- Python 3.8+
+- PyAudio
+- OpenAI Whisper
+- PyTorch
+- NumPy
+- pynput
+
+## License
+
+MIT License
+
+## Author
+
+Erfan Ramezani - erfanramezany245@gmail.com
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.
+
+## Support
+
+For issues and questions, please use the [GitHub Issues](https://github.com/Erfan-ram/whisperpipe/issues) page.

whisperpipe-0.1.0/pyproject.toml

@@ -0,0 +1,67 @@
+[project]
+name = "whisperpipe"
+version = "0.1.0"
+description = "Real-time speech-to-text streaming with OpenAI Whisper"
+authors = [
+    {name = "Erfan Ramezani", email = "erfanramezany245@gmail.com"}
+]
+license = {text = "MIT"}
+readme = "README.md"
+keywords = [
+    "whisper", "openai", "speech-to-text", "stt", "asr",
+    "automatic speech recognition", "real-time", "realtime",
+    "audio", "microphone", "transcription", "streaming", "live transcription"
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: End Users/Desktop",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Operating System :: POSIX :: Linux",
+    "Operating System :: Microsoft :: Windows",
+    "Operating System :: MacOS :: MacOS X",
+    "Environment :: Console",
+    "Topic :: Multimedia :: Sound/Audio :: Speech",
+    "Topic :: Multimedia :: Sound/Audio :: Capture/Recording",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Software Development :: Libraries :: Python Modules"
+]
+requires-python = ">=3.9,<3.13"
+dependencies = [
+    "openai-whisper>=20240930",
+    "pyaudio>=0.2.14",
+    "pynput>=1.7.7",
+    "sounddevice>=0.5.2"
+]
+
+[project.urls]
+Homepage = "https://github.com/Erfan-ram/whisperpipe"
+Repository = "https://github.com/Erfan-ram/whisperpipe"
+Documentation = "https://github.com/Erfan-ram/whisperpipe/blob/main/README.md"
+"Bug Tracker" = "https://github.com/Erfan-ram/whisperpipe/issues"
+"Source" = "https://github.com/Erfan-ram/whisperpipe"
+Changelog = "https://github.com/Erfan-ram/whisperpipe/releases"
+
+[tool.poetry.group.dev.dependencies]
+pytest = "^7.0"
+black = "^23.0"
+flake8 = "^6.0"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = ["test_*.py", "*_test.py"]
+python_functions = ["test_*"]
+addopts = "-v --tb=short"
+filterwarnings = [
+    "ignore::DeprecationWarning",
+    "ignore::PendingDeprecationWarning"
+]

whisperpipe-0.1.0/whisperpipe/__init__.py

@@ -0,0 +1,14 @@
+"""
+whisperpipe - Real-time speech-to-text streaming with OpenAI Whisper
+
+A powerful, easy-to-use package for real-time audio transcription using OpenAI's Whisper model.
+Features include callback support for LLM integration and pause/resume functionality.
+"""
+
+from .core import pipeStream
+
+__version__ = "1.0.0"
+__author__ = "Erfan Ramezani"
+__email__ = "erfanramezany245@gmail.com"
+
+__all__ = ["pipeStream"]