Spaces:

bunyaminergen
/

CallyticsDemo

Running

@@ -1,606 +0,0 @@
-# Contributing to [Project]
-Thank you for your interest in contributing to this project! We’re excited to have you on board. This guide is designed
-to make the contribution process clear and efficient.
----
-## Table of Contents
-1. [How to Contribute?](#how-to-contribute)
-    - [Reporting Issues](#reporting-issues)
-    - [Suggesting Features](#suggesting-features)
-    - [Coding Standards](#coding-standards)
-    - [File Structure](#file-structure)
-    - [Commit Message Guidelines](#commit-message-guidelines)
-    - [Branches](#branches)
-    - [File Naming Convention](#file-naming-convention)
-    - [Versioning, Release, Tag](#versioning-release-tag)
----
-## How to Contribute?
-### Reporting Issues
-- If you find a bug, please open a new issue on the [GitHub Issues](https://github.com/[username]/[project-name]/issues)
-  page.
-- Include the following details:
-    - A clear and descriptive title.
-    - Steps to reproduce the issue.
-    - Expected vs. actual behavior.
-    - Screenshots or error logs if applicable.
-### Suggesting Features
-- Have a great idea for a new feature? Open a new **Issue** and describe your suggestion.
-- Explain how this feature will improve the project.
-### Coding Standards
-##### Import Order
-Follow the import order below to maintain consistency in the codebase:
-1. **Standard library imports**
-2. **Third-party imports**
-3. **Local application/library specific imports**
-**Example:**
-```python
-# Standard library imports
-import os
-import sys
-# Third-party imports
-import numpy as np
-import pandas as pd
-# Local imports
-from my_module import my_function
-```
-> **INFO**
->
-> *For more detail, please check*:
-> - [PEP 8 – Style Guide for Python Code | peps.python.org](https://peps.python.org/pep-0008/)
-##### Docstring
-Use `NumPy` format for docstrings in both functions and classes:
-- Each function or class should have a docstring explaining its purpose, parameters, return values, and examples if
-  applicable.
-- For classes, include a class-level docstring that describes the overall purpose of the class, any parameters for
-  `__init__`, and details on attributes and methods.
-- If you include references (e.g., research papers, algorithms, or external resources) in your docstring, create a
-  separate `References` section clearly listing these sources at the end of your docstring.
-Example for a function:
-```python
-# Standard library imports
-from typing import Annotated
-def example_function(
-    param1: Annotated[int, "Description of param1"],
-    param2: Annotated[str, "Description of param2"]
-) -> Annotated[bool, "Description of the return value"]:
-    """
-    Brief description of what the function does.
-    Parameters
-    ----------
-    param1 : int
-        Description of param1.
-    param2 : str
-        Description of param2.
-    Returns
-    -------
-    bool
-        Description of the return value.
-    Examples
-    --------
-    >>> example_function(5, 'hello')
-    True
-    >>> example_function(0, '')
-    False
-    References
-    ----------
-    * Doe, John. "A Study on Example Functions." Journal of Examples, 2021.
-    """
-    return bool(param1) and bool(param2)
-```
-Example for a class:
-```python
-class MyClass:
-    """
-    MyClass demonstrates the use of docstrings with a separate References section.
-    This class provides an example of structuring docstrings, including attributes,
-    methods, usage examples, and a references section when external sources are cited.
-    Parameters
-    ----------
-    param1 : str
-        Description of `param1`, explaining its purpose and specific constraints.
-    param2 : int, optional
-        Description of `param2`. Defaults to 0.
-    Attributes
-    ----------
-    attribute1 : str
-        Description of `attribute1`, explaining its purpose and possible values.
-    attribute2 : int
-        Description of `attribute2`, outlining constraints or expected values.
-    Methods
-    -------
-    example_method(param1, param2=None)
-        Example method description.
-    Examples
-    --------
-    Create an instance and use methods:
-    >>> my_instance = MyClass("example", 5)
-    >>> my_instance.example_method("sample")
-    References
-    ----------
-    * Smith, Jane. "Guide to Effective Python Documentation." Python Publishing, 2020.
-    * Hu, Jie, Li Shen, and Gang Sun. "Squeeze-and-Excitation Networks."
-      IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.
-    """
-    def __init__(self, param1, param2=0):
-        """
-        Initializes the class.
-        Parameters
-        ----------
-        param1 : str
-            Explanation of `param1`.
-        param2 : int, optional
-            Explanation of `param2`. Defaults to 0.
-        """
-        self.attribute1 = param1
-        self.attribute2 = param2
-    @staticmethod
-    def example_method(param1, param2=None):
-        """
-        Example method.
-        Parameters
-        ----------
-        param1 : str
-            Description of param1.
-        param2 : int, optional
-            Description of param2. Defaults to None.
-        Returns
-        -------
-        bool
-            Outcome of the method's action.
-        """
-        return bool(param1) and bool(param2)
-```
-This structure ensures clear, consistent, and comprehensive documentation of classes and functions, including proper
-citation of external sources.
-##### Type Annotation
-Add type annotations to all functions using `Annotated` with descriptions:
-Example:
-```python
-# Standard library imports
-from typing import Annotated
-def calculate_area(
-    radius: Annotated[float, "Radius of the circle"]
-) -> Annotated[float, "Area of the circle"]:
-    """
-    Calculate the area of a circle given its radius.
-    Parameters
-    ----------
-    radius : float
-        Radius of the circle.
-    Returns
-    -------
-    float
-        Area of the circle.
-    Examples
-    --------
-    >>> calculate_area(5)
-    78.53999999999999
-    >>> calculate_area(0)
-    0.0
-    """
-    if not isinstance(radius, (int, float)):
-        raise TypeError("Expected int or float for parameter 'radius'")
-    if radius < 0:
-        raise ValueError("Radius cannot be negative")
-    return 3.1416 * radius ** 2
-```
-##### Type Check
-Add type check within functions to ensure the correctness of input parameters:
-Example:
-```python
-# Standard library imports
-from typing import Annotated
-def add_numbers(
-    a: Annotated[int, "First integer"],
-    b: Annotated[int, "Second integer"]
-) -> Annotated[int, "Sum of a and b"]:
-    """
-    Add two integers and return the result.
-    Parameters
-    ----------
-    a : int
-        First integer.
-    b : int
-        Second integer.
-    Returns
-    -------
-    int
-        The sum of `a` and `b`.
-    Examples
-    --------
-    >>> add_numbers(2, 3)
-    5
-    >>> add_numbers(-1, 5)
-    4
-    """
-    if not isinstance(a, int):
-        raise TypeError("Expected int for parameter 'a'")
-    if not isinstance(b, int):
-        raise TypeError("Expected int for parameter 'b'")
-    return a + b
-```
-##### Doctest
-Include doctest examples in docstrings using the `>>>` format:
-Example:
-```python
-# Standard library imports
-from typing import Annotated
-def multiply(
-    a: Annotated[int, "First integer"],
-    b: Annotated[int, "Second integer"]
-) -> Annotated[int, "Product of a and b"]:
-    """
-    Multiply two integers and return the result.
-    Parameters
-    ----------
-    a : int
-        First integer.
-    b : int
-        Second integer.
-    Returns
-    -------
-    int
-        The product of `a` and `b`.
-    Examples
-    --------
-    >>> multiply(2, 3)
-    6
-    >>> multiply(-1, 5)
-    -5
-    This is a doctest example.
-    """
-    if not isinstance(a, int):
-        raise TypeError("Expected int for parameter 'a'")
-    if not isinstance(b, int):
-        raise TypeError("Expected int for parameter 'b'")
-    return a * b
-```
-> **INFO**
->
-> *For more detail, please check*:
-> - [doctest — Test interactive Python examples — Python 3.13.1 documentation](https://docs.python.org/3/library/doctest.html)
-##### Main Execution
-Add each file to `Name-Main` code script:
-Example:
-```python
-# Standard library imports
-from typing import Annotated
-def example_function(
-    x: Annotated[int, "An integer parameter"]
-) -> Annotated[int, "The square of x"]:
-    """
-    Calculate the square of an integer.
-    Parameters
-    ----------
-    x : int
-        The integer to be squared.
-    Returns
-    -------
-    int
-        The square of `x`.
-    Examples
-    --------
-    >>> example_function(5)
-    25
-    >>> example_function(-3)
-    9
-    """
-    return x * x
-if __name__ == "__main__":
-    value = 5
-    result = example_function(value)
-    print(f"The square of {value} is {result}.")
-```
-##### General
-- **Always Print Outputs to the Terminal**
-    - Ensure that any significant results or status messages are displayed to the user via `print` statements.
-    - Consider adding an optional parameter (e.g., `verbose=True`) that controls whether to print the outputs. This way,
-      users can disable or enable printed outputs as needed.
-- **Reduce Code Complexity if It Does Not Disrupt the Flow**
-    - Whenever possible, simplify or refactor functions, methods, and classes.
-    - Clear, straightforward logic is easier to maintain and less error-prone.
-- **Keep Your Code Modular at All Times**
-    - Break down larger tasks into smaller, reusable functions or modules.
-    - Modular design improves readability, promotes code reuse, and simplifies testing and maintenance.
-- **Use Base Classes if Classes Become Too Complex**
-    - If a class starts to grow unwieldy or complicated, consider extracting shared logic into a base (parent) class.
-    - Child classes can inherit from this base class, reducing duplication and making the code more organized.
-### File Structure
-Follow the [Default Project Template](https://github.com/bunyaminergen/DefaultProjectTemplate)'s File Structure
-- Adhere to the predetermined file hierarchy and naming conventions defined in the Default Project Template.
-- Review the existing layout in the repository to ensure your contributions align with the project’s organization.
-### Commit Message Guidelines
-- **Keep It Short and Concise:**
-    - The subject line (summary) should typically not exceed **50 characters**.
-    - If more details are needed, include them in the body of the message on a separate line.
-- **Use Present Tense and Imperative Mood:**
-    - **Start your commit message with only of the following verbs** and then explain what you did:
-        - `Add`
-        - `Fix`
-        - `Remove` or `Delete`
-        - `Update`
-        - `Test`
-        - `Refactor`
-    - Messages should use the present tense and imperative mood.
-    - **Examples:**
-        - `Add user authentication`
-        - `Fix bug in payment processing`
-        - `Remove unused dependencies`
-- **Separate Subject and Details:**
-    - The first line (subject) should be short and descriptive.
-    - Leave a blank line between the subject and the detailed description (if needed).
-        - **Example:**
-        ```text
-        Fix login issue
-        Updated the authentication service to handle null values in the session token.
-        ```
-- **Mistakes to Avoid:**
-    - **Vague Messages:**
-        - *Bad Example:* `Fix stuff`, `Update files`, `Work done`.
-    - **Combining Multiple Changes in One Commit:**
-        - Avoid bundling unrelated changes into a single commit.
-    - **Copy-Paste Descriptions:**
-        - Ensure that the commit message is directly relevant to the change.
-- **Benefits of Good Commit Messages:**
-    - A well-written commit history makes the project easier to understand.
-    - It simplifies debugging and troubleshooting.
-    - It improves collaboration within the team by providing clear and meaningful information.
-### Branches
-To maintain consistency across all branches, follow these guidelines:
-- **Start with one of the following action keywords in lowercase:**
-    - `add`
-    - `fix`
-    - `remove` or `delete`
-    - `update`
-    - `test`
-    - `refactor`
-- Use hyphens (`-`) to separate words in the branch name.
-- Avoid special characters, spaces, or uppercase letters.
-- Keep branch names concise but descriptive.
-**Example Branch Names:**
-- `add-new-release`
-- `fix-critical-bug`
-- `remove-unused-dependencies`
-- `update-api-endpoints`
-- `test-api-performance`
-- `refactor-code-structure`
-Please push all development work to the `develop` branch. Once the work on your branch is finished, merge it into
-`develop` and then delete the branch to keep the repository clean.
-**Important:** Please only create branches that begin with the prefixes listed below. If you would like to propose a new
-prefix, kindly open an issue on GitHub.
-##### Bug Branches
-Use the `bugfix/` prefix for bug fixes discovered during development or testing.
-Examples:
-- `bugfix/fix-typo-in-readme`
-- `bugfix/null-pointer-exception`
-##### Feature Branches
-Use the `feature/` prefix for new features or enhancements.
-Examples:
-- `feature/add-login`
-- `feature/update-dashboard`
-- `feature/fix-bug-123`
-##### Hotfix Branches
-Use the `hotfix/` prefix for critical fixes that need immediate attention in production.
-Example:
-- `hotfix/fix-security-issue`
-##### Docfix Branches
-Use the `docfix/` prefix for changes regarding documentation.
-Example:
-- `docfix/add-readme-to-artitecture-section`
-##### Test Branches
-Use the `test/` prefix for branches that focus on writing or updating tests, or conducting specific test-related work.
-Examples:
-- `test/add-integration-tests`
-- `test/refactor-unit-tests`
-- `test/performance-testing`
-##### Experiment Branches
-Use the `experiment/` prefix for experimental or proof-of-concept work.
-Example:
-- `experiment/improve-cache`
----
-### File Naming Convention
-This section explains how packages and modules should be named in this project.
----
-##### Package & Module Naming
-The following rules apply to **both** packages and modules. To simplify these guidelines, the term **"file"** will be
-used as a generic reference to either a package or a module name.
-- **Single or Concise Compound Words:**
-    - Whenever possible, each file name should consist of **a single word** or **a short concatenation of words** (
-      written together).
-    - Use **lowercase letters** only, and **do not** use underscores (`_`).
-      *(Although PEP 8 allows snake_case for modules, we do not prefer it in this project.)*
-    - If more than one word is necessary, write them **together** (e.g., `datautils`, `webparser`).
-- **Consistent Single-Word Usage:**
-    - Especially for package names, aim to keep them to **one word** whenever possible. If multiple words are necessary,
-      the package name should remain **short and clear**.
-- **Parent (Package) and Sub-Component (Module) Logic:**
-    - Use broader, more general names for packages (the “parent”).
-    - For modules (the “child”), use more specific names within the package to reflect their functionality.
-- **Examples:**
-    - **Packages**
-        - `utils`
-        - `model`
-    - **Modules**
-        - `gridsearch.py`
-        - `convolution.py`
-    - **Parent–Child (Directory Structure) Example**
-        - `src/model/backbone.py`
-        - `src/utils/log/manager.py`
-- **Bad Examples:**
-    - **Packages**
-        - `data_reader`  *(underscores are discouraged)*
-    - **Modules**
-        - `grid_search.py`  *(underscores are discouraged)*
-    - **Parent–Child (Directory Structure) Example**
-        - `src/train/training.py`  *(names are too similar or redundant)*
----
-##### Test Files
-1. **Using the `test_` Prefix:**
-    - For test files, prepend `test_` to the **module** name being tested.
-    - **Example:** If the module name is `dataprocess.py`, then the test file should be named `test_dataprocess.py`.
-> **INFO**
-> *For more details, please check:*
-> - [PEP 8 – Style Guide for Python Code | peps.python.org](https://peps.python.org/pep-0008/#:~:text=Modules%20should%20have%20short%2C%20all,use%20of%20underscores%20is%20discouraged)
-> - [PEP 423 – Naming conventions and recipes related to packaging | peps.python.org](https://peps.python.org/pep-0423/#follow-pep-8-for-syntax-of-package-and-module-names)
----
-### Versioning, Release, Tag
-- When numbering versions, releases, or tags, **only use prime numbers** (e.g., 3, 5, 7, 11, 13...).
-- **Do not** use 2 (even though it is prime) or any non-prime numbers (4, 6, 8, 9, 10...).
-#### Examples
-**Good Examples** (using only prime numbers, excluding 2):
-- **Tag**: `v3`
-- **Release**: `v3.5.7`
-- **Version**: `5.7.11`
-**Bad Examples**:
-- **Tag**: `v2` *(2 is prime but disallowed in this project)*
-- **Release**: `v1.2.3` *(1 is not prime, 2 is disallowed, 3 is prime but the rest are invalid)*
-- **Version**: `4.6.8` *(4, 6, 8 are not prime)*
----

.docs/documentation/RESOURCES.md DELETED Viewed

@@ -1,119 +0,0 @@
-# Resources
----
-## Github
-- [NeMo](https://github.com/NVIDIA/NeMo)
-- [Llama](https://github.com/facebookresearch/llama)
-- [Demucs](https://github.com/facebookresearch/demucs)
-- [Whisper](https://github.com/openai/whisper)
-- [Whisper NeMo Diarization](https://github.com/MahmoudAshraf97/whisper-diarization)
-- [Text to speech alignment using CTC forced alignment](https://github.com/MahmoudAshraf97/ctc-forced-aligner)
-- [Utilities intended for use with Llama models.](https://github.com/meta-llama/llama-models/)
-- [Llama Recipes: Examples to get started using the Llama models from Meta](https://github.com/meta-llama/llama-recipes)
-- [timsainb/noisereduce: Noise reduction in python using spectral gating](https://github.com/timsainb/noisereduce/)
-- [pyannote/pyannote-audio: Neural building blocks for speaker diarization](https://github.com/pyannote/pyannote-audio)
-- [microsoft/DNS-Challenge: This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.](https://github.com/microsoft/DNS-Challenge)
-- [WenzheLiu-Speech/awesome-speech-enhancement: speech enhancement\speech seperation\sound source localization](https://github.com/WenzheLiu-Speech/awesome-speech-enhancement)
-- [nanahou/Awesome-Speech-Enhancement: A tutorial for Speech Enhancement researchers and practitioners. The purpose of this repo is to organize the world’s resources for speech enhancement and make them universally accessible and useful.](https://github.com/nanahou/Awesome-Speech-Enhancement)
-- [jonashaag/speech-enhancement: Collection of papers, datasets and tools on the topic of Speech Dereverberation and Speech Enhancement](https://github.com/jonashaag/speech-enhancement)
-- [yxlu-0102/MP-SENet: Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement](https://github.com/yxlu-0102/MP-SENet)
-- [Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement](https://yxlu-0102.github.io/MP-SENet/)
-- [## SUPERSEDED: THIS DATASET HAS BEEN REPLACED. ## Noisy speech database for training speech enhancement algorithms and TTS models](https://datashare.ed.ac.uk/handle/10283/1942)
----
-## Web
-- [Llama](https://www.llama.com/)
-- [Download Llama](https://www.llama.com/llama-downloads/)
-- [Llama 3.2 Requirements](https://llamaimodel.com/requirements-3-2/)
-- [Average handle time (AHT): Formula and tips for improvement](https://www.zendesk.com/blog/average-handle-time/)
----
-## Notebooks
-- [Hybrid Demucs Music Source Separation](https://colab.research.google.com/drive/1dC9nVxk3V_VPjUADsnFu8EiT-xnU1tGH)
----
-## PyPI
-- [demucs](https://pypi.org/project/demucs/)
-- [MPSENet](https://pypi.org/project/MPSENet/)
----
-## Errors
-- [`The file is already fully retrieved; nothing to do.`](https://github.com/facebookresearch/llama/issues/760)
----
-## Paper
-- [Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation](https://arxiv.org/abs/2007.13975)
-- [MP-SENet: A Speech Enhancement Model with Parallel Denoising of Magnitude and Phase Spectra](https://arxiv.org/abs/2305.13686)
-- [FINALLY: fast and universal speech enhancement with studio-like quality](https://arxiv.org/abs/2410.05920)
-- [Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement](https://arxiv.org/abs/2308.08926)
-- [\[2410.08235\] A Recurrent Neural Network Approach to the Answering Machine Detection Problem](https://arxiv.org/abs/2410.08235)
----
-## Youtube
-- [A Course on Speech Enhancement](https://www.youtube.com/playlist?list=PLO9nFIQB53_DU8o0fToNdNFdZuDxD9fAN)
-- [COMS 4995 Final on Speech Enhancement](https://www.youtube.com/watch?v=uRwlSh1FMzc&t=74s)
-- [Achieving Studio-Quality Speech with Generative AI](https://www.youtube.com/watch?v=UxbEjpLMU8s)
-- [How to Fix Bad Podcast Audio](https://www.youtube.com/watch?v=0mPkPQNHsZc)
-- [Speech Enhancement for Cochlear Implant Recipients Using Deep Complex Convolution Transformer With F](https://www.youtube.com/watch?v=i1qTgjMtS2Y)
-- [Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors](https://www.youtube.com/watch?v=4jiQdotz6qY)
-- [2024 종합설계 3팀 2차, Neural Network for Speech Enhancement](https://www.youtube.com/watch?v=yOfTYuc9FEQ)
-- [MIAI Deeptails Seminar : Generative Models as Data-driven Priors for Speech Enhancement](https://www.youtube.com/watch?v=XSLgUsgyzUA)
-- [Hardware Efficient Speech Enhancement With Noise Aware Multi Target Deep Learning](https://www.youtube.com/watch?v=qO6JqDUQlsI)
-- [Diffusion Models for Speech Enhancement | Julius Richter](https://www.youtube.com/watch?v=HMrs6YWDl5M)
-- [Speech Enhancement: Basics & Key Details](https://www.youtube.com/watch?v=5kItH2pq_3E)
-- [Guided Speech Enhancement Network (ICASSP 2023)](https://www.youtube.com/watch?v=JoDqXkAjlh4)
-- [VSANet: Real-time Speech Enhancement Based on Voice Activity Detection and Causal Spatial Attention](https://www.youtube.com/watch?v=GP39vFA2E48)
-- [Research intern talk: Unified speech enhancement approach for speech degradation & noise suppression](https://www.youtube.com/watch?v=_ggfv6eMIJs)
-- [Magnitude and phase spectrum with example](https://www.youtube.com/watch?v=MFOjUgafq0k)
-- [Deep Learning In Audio for Absolute Beginners: From No Experience & No Datasets to a Deployed Model](https://www.youtube.com/watch?v=sqrah49GUkI)
-- [Look Once to Hear: Target Speech Hearing with Noisy Examples](https://www.youtube.com/watch?v=V-XCfnjfQmM)
----
-## Wikipedia
-- [Speech enhancement](https://en.m.wikipedia.org/wiki/Speech_enhancement)
----
-## Hugging Face
-- [Models(asteroid)](https://huggingface.co/models?library=asteroid)
-- [cankeles/DPTNet_WHAMR_enhsingle_16k](https://huggingface.co/cankeles/DPTNet_WHAMR_enhsingle_16k)
-- [JacobLinCool/MP-SENet-VB](https://huggingface.co/JacobLinCool/MP-SENet-VB)
-- [JacobLinCool/MP-SENet-DNS](https://huggingface.co/JacobLinCool/MP-SENet-DNS)
-- [ENOT-AutoDL/MP-SENet](https://huggingface.co/ENOT-AutoDL/MP-SENet)
----
-## Web
-- [Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation](https://paperswithcode.com/paper/dual-path-transformer-network-direct-context-1)
-- [The Audio Developer Conference - ADC is an annual event celebrating all audio development technologies, from music applications and game audio to audio processing and embedded systems.](https://audio.dev/)
-- [Look Once to Hear: Target Speech Hearing with Noisy Examples - CHI '24](https://programs.sigchi.org/chi/2024/program/content/147319)
-- [Reinforcement Learning Based Speech Enhancement for Robust Speech Recognition > Introduction | Class Central Classroom](https://www.classcentral.com/classroom/youtube-reinforcement-learning-based-speech-enhancement-for-robust-speech-recognition-131999)
-- [Sound classification with YAMNet TensorFlow Hub](https://www.tensorflow.org/hub/tutorials/yamnet)
-- [DEEP-VOICE: DeepFake Voice Recognition Dataset | Papers With Code](https://paperswithcode.com/dataset/deep-voice-deepfake-voice-recognition)
----
-## Dataset
-- [VoiceBank+DEMAND](https://datashare.ed.ac.uk/handle/10283/1942)
-- [VoiceBank+DEMAND](https://drive.google.com/drive/folders/19I_thf6F396y5gZxLTxYIojZXC0Ywm8l)
----

.docs/img/Callytics.drawio DELETED Viewed

@@ -1,164 +0,0 @@
-<mxfile host="Electron" agent="Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) draw.io/25.0.1 Chrome/128.0.6613.186 Electron/32.2.6 Safari/537.36" version="25.0.1">
-  <diagram name="Page-1" id="mQKUGW6_SND0Kw_IrtOi">
-    <mxGraphModel dx="1829" dy="896" grid="1" gridSize="10" guides="1" tooltips="1" connect="1" arrows="1" fold="1" page="0" pageScale="1" pageWidth="1600" pageHeight="900" math="0" shadow="0">
-      <root>
-        <mxCell id="0" />
-        <mxCell id="1" parent="0" />
-        <mxCell id="5rAtEOWpySoy4L2wUreW-1" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;flowAnimation=1;" edge="1" parent="1" source="5rAtEOWpySoy4L2wUreW-2" target="5rAtEOWpySoy4L2wUreW-3">
-          <mxGeometry relative="1" as="geometry">
-            <Array as="points">
-              <mxPoint x="70" y="453" />
-            </Array>
-          </mxGeometry>
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-2" value="&lt;i&gt;&lt;b&gt;Input&lt;br&gt;(Audio File)&lt;/b&gt;&lt;/i&gt;" style="ellipse;whiteSpace=wrap;html=1;aspect=fixed;fillColor=default;strokeWidth=3;" vertex="1" parent="1">
-          <mxGeometry x="20" y="230" width="105" height="105" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-3" value="" style="shape=cylinder3;whiteSpace=wrap;html=1;boundedLbl=1;backgroundOutline=1;size=15;rotation=90;strokeWidth=3;fillColor=default;" vertex="1" parent="1">
-          <mxGeometry x="857.33" y="-321.46" width="141.5" height="1578.78" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-4" style="rounded=0;orthogonalLoop=1;jettySize=auto;html=1;flowAnimation=1;endArrow=none;endFill=0;" edge="1" parent="1" source="5rAtEOWpySoy4L2wUreW-5" target="5rAtEOWpySoy4L2wUreW-8">
-          <mxGeometry relative="1" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-5" value="&lt;div&gt;&lt;b&gt;Dialogue&amp;nbsp;&lt;br&gt;Detection&lt;/b&gt;&lt;/div&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.stored_data;whiteSpace=wrap;spacingLeft=8;spacingRight=4;spacingBottom=3;direction=west;" vertex="1" parent="1">
-          <mxGeometry x="160" y="422.5" width="100" height="60" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-6" value="&lt;font style=&quot;font-size: 9px;&quot;&gt;&lt;i&gt;Pyannote&lt;/i&gt;&lt;/font&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.document2;whiteSpace=wrap;size=0.25;" vertex="1" parent="1">
-          <mxGeometry x="176" y="482.94" width="68" height="37" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-7" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;endArrow=none;endFill=0;flowAnimation=1;" edge="1" parent="1" source="5rAtEOWpySoy4L2wUreW-8" target="5rAtEOWpySoy4L2wUreW-10">
-          <mxGeometry relative="1" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-8" value="&lt;b&gt;Speech Enhancement&lt;/b&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.stored_data;whiteSpace=wrap;spacingLeft=8;spacingRight=4;spacingBottom=3;direction=west;" vertex="1" parent="1">
-          <mxGeometry x="270" y="422.94" width="100" height="60" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-9" value="&lt;font size=&quot;1&quot;&gt;&lt;i&gt;MP-SENet&lt;/i&gt;&lt;/font&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.document2;whiteSpace=wrap;size=0.25;" vertex="1" parent="1">
-          <mxGeometry x="286" y="482.94" width="68" height="37" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-10" value="&lt;b&gt;Vocal&lt;/b&gt;&lt;div&gt;&lt;b&gt;Seperation&lt;/b&gt;&lt;/div&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.stored_data;whiteSpace=wrap;spacingLeft=8;spacingRight=4;spacingBottom=3;direction=west;" vertex="1" parent="1">
-          <mxGeometry x="380" y="422.5" width="100" height="60" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-11" value="&lt;font style=&quot;font-size: 9px;&quot;&gt;&lt;i&gt;Demucs&lt;/i&gt;&lt;/font&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.document2;whiteSpace=wrap;size=0.25;" vertex="1" parent="1">
-          <mxGeometry x="396" y="482.5" width="68" height="37" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-12" value="&lt;b&gt;Transcription&lt;/b&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.stored_data;whiteSpace=wrap;spacingLeft=8;spacingRight=4;spacingBottom=3;direction=west;" vertex="1" parent="1">
-          <mxGeometry x="494" y="422.94" width="100" height="60" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-13" value="&lt;font style=&quot;font-size: 9px;&quot;&gt;&lt;i&gt;Faster Whisper&lt;/i&gt;&lt;/font&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.document2;whiteSpace=wrap;size=0.25;" vertex="1" parent="1">
-          <mxGeometry x="510" y="482.94" width="68" height="37" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-14" value="&lt;b&gt;Forced Alignment&lt;/b&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.stored_data;whiteSpace=wrap;spacingLeft=8;spacingRight=4;spacingBottom=3;direction=west;" vertex="1" parent="1">
-          <mxGeometry x="610" y="422.5" width="100" height="60" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-15" value="&lt;div style=&quot;&quot;&gt;&lt;i style=&quot;font-size: 9px; background-color: initial; line-height: 100%;&quot;&gt;ctc forced aligner&lt;/i&gt;&lt;/div&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.document2;whiteSpace=wrap;size=0.25;align=center;" vertex="1" parent="1">
-          <mxGeometry x="626" y="482.5" width="68" height="37" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-16" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0.93;entryY=0.5;entryDx=0;entryDy=0;entryPerimeter=0;endArrow=none;endFill=0;flowAnimation=1;" edge="1" parent="1" source="5rAtEOWpySoy4L2wUreW-12" target="5rAtEOWpySoy4L2wUreW-14">
-          <mxGeometry relative="1" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-17" value="&lt;b&gt;Diarization&lt;/b&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.stored_data;whiteSpace=wrap;spacingLeft=8;spacingRight=4;spacingBottom=3;direction=west;" vertex="1" parent="1">
-          <mxGeometry x="730" y="422.5" width="100" height="60" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-18" value="&lt;font size=&quot;1&quot;&gt;&lt;i&gt;Nvidia Nemo&lt;/i&gt;&lt;/font&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.document2;whiteSpace=wrap;size=0.25;" vertex="1" parent="1">
-          <mxGeometry x="746" y="482.5" width="68" height="37" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-19" value="&lt;b&gt;Speaker Role&lt;br&gt;Classification&lt;/b&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.stored_data;whiteSpace=wrap;spacingLeft=8;spacingRight=4;spacingBottom=3;direction=west;" vertex="1" parent="1">
-          <mxGeometry x="850" y="422.94" width="100" height="60" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-20" value="&lt;font size=&quot;1&quot;&gt;&lt;i&gt;LLM&lt;/i&gt;&lt;/font&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.document2;whiteSpace=wrap;size=0.25;" vertex="1" parent="1">
-          <mxGeometry x="866" y="482.94" width="68" height="37" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-21" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0.93;entryY=0.5;entryDx=0;entryDy=0;entryPerimeter=0;endArrow=none;endFill=0;flowAnimation=1;" edge="1" parent="1" source="5rAtEOWpySoy4L2wUreW-17" target="5rAtEOWpySoy4L2wUreW-19">
-          <mxGeometry relative="1" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-22" value="&lt;b&gt;Sentiment&lt;/b&gt;&lt;div&gt;&lt;b&gt;Analysis&lt;/b&gt;&lt;/div&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.stored_data;whiteSpace=wrap;spacingLeft=8;spacingRight=4;spacingBottom=3;direction=west;" vertex="1" parent="1">
-          <mxGeometry x="970" y="422.94" width="100" height="60" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-23" value="&lt;font size=&quot;1&quot;&gt;&lt;i&gt;LLM&lt;/i&gt;&lt;/font&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.document2;whiteSpace=wrap;size=0.25;" vertex="1" parent="1">
-          <mxGeometry x="986" y="485.44" width="68" height="37" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-24" value="&lt;b&gt;Profanity Word Detection&lt;/b&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.stored_data;whiteSpace=wrap;spacingLeft=8;spacingRight=4;spacingBottom=3;direction=west;" vertex="1" parent="1">
-          <mxGeometry x="1090" y="422.5" width="100" height="60" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-25" value="&lt;font size=&quot;1&quot;&gt;&lt;i&gt;LLM&lt;/i&gt;&lt;/font&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.document2;whiteSpace=wrap;size=0.25;" vertex="1" parent="1">
-          <mxGeometry x="1106" y="482.5" width="68" height="37" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-26" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0.93;entryY=0.5;entryDx=0;entryDy=0;entryPerimeter=0;flowAnimation=1;endArrow=none;endFill=0;" edge="1" parent="1" source="5rAtEOWpySoy4L2wUreW-22" target="5rAtEOWpySoy4L2wUreW-24">
-          <mxGeometry relative="1" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-27" value="&lt;b&gt;Summary&lt;/b&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.stored_data;whiteSpace=wrap;spacingLeft=8;spacingRight=4;spacingBottom=3;direction=west;" vertex="1" parent="1">
-          <mxGeometry x="1213" y="422.5" width="100" height="60" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-28" value="&lt;font size=&quot;1&quot;&gt;&lt;i&gt;LLM&lt;/i&gt;&lt;/font&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.document2;whiteSpace=wrap;size=0.25;" vertex="1" parent="1">
-          <mxGeometry x="1229" y="482.5" width="68" height="37" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-29" value="&lt;b&gt;Conflict Detection&lt;/b&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.stored_data;whiteSpace=wrap;spacingLeft=8;spacingRight=4;spacingBottom=3;direction=west;" vertex="1" parent="1">
-          <mxGeometry x="1330" y="422.5" width="100" height="60" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-30" value="&lt;font size=&quot;1&quot;&gt;&lt;i&gt;LLM&lt;/i&gt;&lt;/font&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.document2;whiteSpace=wrap;size=0.25;" vertex="1" parent="1">
-          <mxGeometry x="1346" y="482.94" width="68" height="37" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-31" value="&lt;b&gt;Topic Detection&lt;/b&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.stored_data;whiteSpace=wrap;spacingLeft=8;spacingRight=4;spacingBottom=3;direction=west;" vertex="1" parent="1">
-          <mxGeometry x="1450" y="422.94" width="100" height="60" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-32" value="&lt;font size=&quot;1&quot;&gt;&lt;i&gt;LLM&lt;/i&gt;&lt;/font&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.document2;whiteSpace=wrap;size=0.25;" vertex="1" parent="1">
-          <mxGeometry x="1466" y="482.94" width="68" height="37" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-33" value="&lt;b&gt;Storage&lt;/b&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.stored_data;whiteSpace=wrap;spacingLeft=8;spacingRight=4;spacingBottom=3;direction=west;" vertex="1" parent="1">
-          <mxGeometry x="1570" y="422.5" width="100" height="60" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-34" value="&lt;font size=&quot;1&quot;&gt;&lt;i&gt;Database&lt;/i&gt;&lt;/font&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.document2;whiteSpace=wrap;size=0.25;" vertex="1" parent="1">
-          <mxGeometry x="1586" y="485.44" width="68" height="37" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-35" value="&lt;b&gt;Monitoring&amp;nbsp;&lt;br&gt;&lt;/b&gt;&lt;div&gt;&lt;b&gt;&amp;amp;&amp;nbsp;&lt;/b&gt;&lt;/div&gt;&lt;div&gt;&lt;b&gt;Alarms&lt;/b&gt;&lt;/div&gt;" style="verticalLabelPosition=middle;verticalAlign=middle;html=1;shape=mxgraph.basic.three_corner_round_rect;dx=6;whiteSpace=wrap;labelPosition=center;align=center;" vertex="1" parent="1">
-          <mxGeometry x="1760" y="422.5" width="140" height="90" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-36" value="&lt;font size=&quot;1&quot;&gt;&lt;i&gt;Grafana&lt;/i&gt;&lt;/font&gt;" style="strokeWidth=2;html=1;shape=mxgraph.flowchart.document2;whiteSpace=wrap;size=0.25;" vertex="1" parent="1">
-          <mxGeometry x="1796" y="512.94" width="68" height="37" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-37" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0;entryY=0.5;entryDx=0;entryDy=0;entryPerimeter=0;endArrow=classic;endFill=1;flowAnimation=1;" edge="1" parent="1" source="5rAtEOWpySoy4L2wUreW-3" target="5rAtEOWpySoy4L2wUreW-35">
-          <mxGeometry relative="1" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-38" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0.93;entryY=0.5;entryDx=0;entryDy=0;entryPerimeter=0;flowAnimation=1;endArrow=none;endFill=0;" edge="1" parent="1" source="5rAtEOWpySoy4L2wUreW-10" target="5rAtEOWpySoy4L2wUreW-12">
-          <mxGeometry relative="1" as="geometry" />
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-39" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0.93;entryY=0.5;entryDx=0;entryDy=0;entryPerimeter=0;endArrow=none;endFill=0;flowAnimation=1;exitX=0;exitY=0.5;exitDx=0;exitDy=0;exitPerimeter=0;" edge="1" parent="1" source="5rAtEOWpySoy4L2wUreW-14" target="5rAtEOWpySoy4L2wUreW-17">
-          <mxGeometry relative="1" as="geometry">
-            <mxPoint x="710" y="452.41" as="sourcePoint" />
-            <mxPoint x="733" y="452.41" as="targetPoint" />
-          </mxGeometry>
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-40" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0.93;entryY=0.5;entryDx=0;entryDy=0;entryPerimeter=0;endArrow=none;endFill=0;flowAnimation=1;" edge="1" parent="1">
-          <mxGeometry relative="1" as="geometry">
-            <mxPoint x="950" y="452.4" as="sourcePoint" />
-            <mxPoint x="977" y="452.4" as="targetPoint" />
-          </mxGeometry>
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-41" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0.93;entryY=0.5;entryDx=0;entryDy=0;entryPerimeter=0;flowAnimation=1;endArrow=none;endFill=0;" edge="1" parent="1">
-          <mxGeometry relative="1" as="geometry">
-            <mxPoint x="1190" y="452.87" as="sourcePoint" />
-            <mxPoint x="1217" y="452.87" as="targetPoint" />
-          </mxGeometry>
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-42" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0.93;entryY=0.5;entryDx=0;entryDy=0;entryPerimeter=0;endArrow=none;endFill=0;flowAnimation=1;" edge="1" parent="1">
-          <mxGeometry relative="1" as="geometry">
-            <mxPoint x="1430" y="452.84" as="sourcePoint" />
-            <mxPoint x="1454" y="452.84" as="targetPoint" />
-          </mxGeometry>
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-43" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0.93;entryY=0.5;entryDx=0;entryDy=0;entryPerimeter=0;endArrow=none;endFill=0;flowAnimation=1;" edge="1" parent="1">
-          <mxGeometry relative="1" as="geometry">
-            <mxPoint x="1313" y="452.45" as="sourcePoint" />
-            <mxPoint x="1337" y="452.45" as="targetPoint" />
-          </mxGeometry>
-        </mxCell>
-        <mxCell id="5rAtEOWpySoy4L2wUreW-44" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;entryX=0.93;entryY=0.5;entryDx=0;entryDy=0;entryPerimeter=0;endArrow=none;endFill=0;flowAnimation=1;" edge="1" parent="1">
-          <mxGeometry relative="1" as="geometry">
-            <mxPoint x="1550" y="452.45" as="sourcePoint" />
-            <mxPoint x="1574" y="452.45" as="targetPoint" />
-          </mxGeometry>
-        </mxCell>
-      </root>
-    </mxGraphModel>
-  </diagram>
-</mxfile>

.docs/img/Callytics.gif DELETED Viewed

Git LFS Details

SHA256: cccf7f416c745e58bb1106187e90157f0fb4c0b3307750a961ba92a9f2dae8b4
Pointer size: 131 Bytes
Size of remote file: 286 kB

.docs/img/Callytics.png DELETED Viewed

Git LFS Details

SHA256: 56954553615e7211d696f267621af9572e2e11eace167010f52df19872c49c6a
Pointer size: 130 Bytes
Size of remote file: 86.3 kB

.docs/img/Callytics.svg DELETED Viewed

.docs/img/CallyticsIcon.png DELETED Viewed

Git LFS Details

SHA256: f57d0f56528a07cb956c463335f2ed88db1e0dc5f309c64bb1452559cba92c3b
Pointer size: 131 Bytes
Size of remote file: 307 kB

.docs/img/callyticsDemo.gif DELETED Viewed

Git LFS Details

SHA256: 589b4b3cae9a70f71b7bd1e1be1b28eb8fe35ef5bb7e0801f3c596bef08d6e0d
Pointer size: 132 Bytes
Size of remote file: 6.1 MB

.docs/img/database.png DELETED Viewed

Git LFS Details

SHA256: 9adcab2d82324a8cdc246bf4179587f4b3f4a795822e224ec426b1db3db4eb80
Pointer size: 131 Bytes
Size of remote file: 183 kB

.docs/presentation/CallyticsPresentationEN.pdf DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:eeeb65cf46a72a930f855b561b403f6e9cd42b5fb178f8aa7fa0fa97c3d42afd
-size 16425335

.gitattributes CHANGED Viewed

@@ -33,9 +33,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-# CallyticsDemo
-*.pdf filter=lfs diff=lfs merge=lfs -text
-*.mp3 filter=lfs diff=lfs merge=lfs -text
-*.wav filter=lfs diff=lfs merge=lfs -text
-*.png filter=lfs diff=lfs merge=lfs -text
-*.gif filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

.github/CODEOWNERS DELETED Viewed

	@@ -1 +0,0 @@
1	- * @bunyaminergen

.gitignore CHANGED Viewed

@@ -4,5 +4,5 @@
 .agile
 .data/input
-# Extension
 *.env

 .agile
 .data/input
+# File
 *.env

README.md DELETED Viewed

@@ -1,552 +0,0 @@
----
-title: Callytics Demo
-emoji: 🚀
-colorFrom: green
-colorTo: purple
-sdk: gradio
-sdk_version: 5.23.1
-app_file: app.py
-pinned: false
-license: gpl-3.0
-short_description: Callytics Demo
----
-<div align="center">
-<img src=".docs/img/CallyticsIcon.png" alt="CallyticsLogo" width="200">
-![License](https://img.shields.io/github/license/bunyaminergen/Callytics)
-![GitHub release (latest by date)](https://img.shields.io/github/v/release/bunyaminergen/Callytics)
-![GitHub Discussions](https://img.shields.io/github/discussions/bunyaminergen/Callytics)
-![GitHub Issues](https://img.shields.io/github/issues/bunyaminergen/Callytics)
-[![LinkedIn](https://img.shields.io/badge/LinkedIn-Profile-blue?logo=linkedin)](https://linkedin.com/in/bunyaminergen)
-# Callytics
-`Callytics` is an advanced call analytics solution that leverages speech recognition and large language models (LLMs)
-technologies to analyze phone conversations from customer service and call centers. By processing both the
-audio and text of each call, it provides insights such as sentiment analysis, topic detection, conflict detection,
-profanity word detection and summary. These cutting-edge techniques help businesses optimize customer interactions,
-identify areas for improvement, and enhance overall service quality.
-When an audio file is placed in the `.data/input` directory, the entire pipeline automatically starts running, and the
-resulting data is inserted into the database.
-**Note**: _This is only a `v1.1.0` version; many new features will be added, models
-will be fine-tuned or trained from scratch, and various optimization efforts will be applied. For more information,
-you can check out the [Upcoming](#upcoming) section._
-**Note**: _If you would like to contribute to this repository,
-please read the [CONTRIBUTING](.docs/documentation/CONTRIBUTING.md) first._
-</div>
----
-### Table of Contents
-- [Prerequisites](#prerequisites)
-- [Architecture](#architecture)
-- [Math And Algorithm](#math-and-algorithm)
-- [Features](#features)
-- [Demo](#demo)
-- [Installation](#installation)
-- [File Structure](#file-structure)
-- [Database Structure](#database-structure)
-- [Version Control System](#version-control-system)
-- [Upcoming](#upcoming)
-- [Documentations](#documentations)
-- [License](#licence)
-- [Links](#links)
-- [Team](#team)
-- [Contact](#contact)
-- [Citation](#citation)
----
-### Prerequisites
-##### General
-- `Python 3.11` _(or above)_
-##### Llama
-- `GPU (min 24GB)` _(or above)_
-- `Hugging Face Credentials (Account, Token)`
-- `Llama-3.2-11B-Vision-Instruct` _(or above)_
-##### OpenAI
-- `GPU (min 12GB)` _(for other process such as `faster whisper` & `NeMo`)_
-- At least one of the following is required:
-    - `OpenAI Credentials (Account, API Key)`
-    - `Azure OpenAI Credentials (Account, API Key, API Base URL)`
----
-### Architecture
-![Architecture](.docs/img/Callytics.gif)
----
-### Math and Algorithm
-This section describes the mathematical models and algorithms used in the project.
-_**Note**: The mathematical concepts and algorithms specific to this repository, rather than the models used, will be
-provided in this section. Please refer to the `RESOURCES` under the [Documentations](#documentations) section for the
-repositories and models utilized or referenced._
-##### Silence Duration Calculation
-The silence durations are derived from the time intervals between speech segments:
-$$S = \{s_1, s_2, \ldots, s_n\}$$
-represent _the set of silence durations (in seconds)_ between consecutive speech segments.
-- **A user-defined factor**:
-$$\text{factor} \in \mathbb{R}^{+}$$
-To determine a threshold that distinguishes _significant_ silence from trivial gaps, two statistical methods can be
-applied:
-**1. Standard Deviation-Based Threshold**
-- _Mean_:
-$$\mu = \frac{1}{n}\sum_{i=1}^{n}s_i$$
-- _Standard Deviation_:
-$$
-\sigma = \sqrt{\frac{1}{n}\sum_{i=1}^{n}(s_i - \mu)^2}
-$$
-- _Threshold_:
-$$
-T_{\text{std}} = \sigma \cdot \text{factor}
-$$
-**2. Median + Interquartile Range (IQR) Threshold**
-- _Median_:
-_Let:_
-$$ S = \{s_{(1)} \leq s_{(2)} \leq \cdots \leq s_{(n)}\} $$
-be an ordered set.
-_Then:_
-$$
-M = \text{median}(S) =
-\begin{cases}
-s_{\frac{n+1}{2}}, & \text{if } n \text{ is odd}, \\\\[6pt]
-\frac{s_{\frac{n}{2}} + s_{\frac{n}{2}+1}}{2}, & \text{if } n \text{ is even}.
-\end{cases}
-$$
-- _Quartiles:_
-$$
-Q_1 = s_{(\lfloor 0.25n \rfloor)}, \quad Q_3 = s_{(\lfloor 0.75n \rfloor)}
-$$
-- _IQR_:
-$$
-\text{IQR} = Q_3 - Q_1
-$$
-- **Threshold:**
-$$
-T_{\text{median\\_iqr}} = M + (\text{IQR} \times \text{factor})
-$$
-**Total Silence Above Threshold**
-Once the threshold
-$$T$$
-either
-$$T_{\text{std}}$$
-or
-$$T_{\text{median\\_iqr}}$$
-is defined, we sum only those silence durations that meet or exceed this threshold:
-$$
-\text{TotalSilence} = \sum_{i=1}^{n} s_i \cdot \mathbf{1}(s_i \geq T)
-$$
-where $$\mathbf{1}(s_i \geq T)$$ is an indicator function defined as:
-$$
-\mathbf{1}(s_i \geq T) =
-\begin{cases}
-1 & \text{if } s_i \geq T \\
-0 & \text{otherwise}
-\end{cases}
-$$
-**Summary:**
-- **Identify the silence durations:**
-$$
-S = \{s_1, s_2, \ldots, s_n\}
-$$
-- **Determine the threshold using either:**
-_Standard deviation-based:_
-$$
-T = \sigma \cdot \text{factor}
-$$
-_Median+IQR-based:_
-$$
-T = M + (\text{IQR} \cdot \text{factor})
-$$
-- **Compute the total silence above this threshold:**
-$$
-\text{TotalSilence} = \sum_{i=1}^{n} s_i \cdot \mathbf{1}(s_i \geq T)
-$$
----
-### Features
-- [x] Speech Enhancement
-- [x] Sentiment Analysis
-- [x] Profanity Word Detection
-- [x] Summary
-- [x] Conflict Detection
-- [x] Topic Detection
----
-### Demo
-![callyticsDemo](.docs/img/callyticsDemo.gif)
----
-### Installation
-##### Linux/Ubuntu
-```bash
-sudo apt update -y && sudo apt upgrade -y
-```
-```bash
-sudo apt install ffmpeg -y
-```
-```bash
-sudo apt install -y ffmpeg build-essential g++
-```
-```bash
-git clone https://github.com/bunyaminergen/Callytics
-```
-```bash
-cd Callytics
-```
-```bash
-conda env create -f environment.yaml
-```
-```bash
-conda activate Callytics
-```
-##### Environment
-`.env` file sample:
-```Text
-# CREDENTIALS
-# OPENAI
-OPENAI_API_KEY=
-# HUGGINGFACE
-HUGGINGFACE_TOKEN=
-# AZURE OPENAI
-AZURE_OPENAI_API_KEY=
-AZURE_OPENAI_API_BASE=
-AZURE_OPENAI_API_VERSION=
-# DATABASE
-DB_NAME=
-DB_USER=
-DB_PASSWORD=
-DB_HOST=
-DB_PORT=
-DB_URL=
-```
----
-##### Database
-_In this section, an `example database` and `tables` are provided. It is a `well-structured` and `simple design`. If you
-create the tables
-and columns in the same structure in your remote database, you will not encounter errors in the code. However, if you
-want to change the database structure, you will also need to refactor the code._
-*Note*: __Refer to the [Database Structure](#database-structure) section for the database schema and tables.__
-```bash
-sqlite3 .db/Callytics.sqlite < src/db/sql/Schema.sql
-```
-##### Grafana
-_In this section, it is explained how to install `Grafana` on your `local` environment. Since Grafana is a third-party
-open-source monitoring application, you must handle its installation yourself and connect your database. Of course, you
-can also use it with `Granafa Cloud` instead of `local` environment._
-```bash
-sudo apt update -y && sudo apt upgrade -y
-```
-```bash
-sudo apt install -y apt-transport-https software-properties-common wget
-```
-```bash
-wget -q -O - https://packages.grafana.com/gpg.key | sudo apt-key add -
-```
-```bash
-echo "deb https://packages.grafana.com/oss/deb stable main" | sudo tee /etc/apt/sources.list.d/grafana.list
-```
-```bash
-sudo apt install -y grafana
-```
-```bash
-sudo systemctl start grafana-server
-sudo systemctl enable grafana-server
-sudo systemctl daemon-reload
-```
-```bash
-http://localhost:3000
-```
-**SQLite Plugin**
-```bash
-sudo grafana-cli plugins install frser-sqlite-datasource
-```
-```bash
-sudo systemctl restart grafana-server
-```
-```bash
-sudo systemctl daemon-reload
-```
-### File Structure
-```Text
-.
-├── automation
-│         └── service
-│             └── callytics.service
-├── config
-│         ├── config.yaml
-│         ├── nemo
-│         │         └── diar_infer_telephonic.yaml
-│         └── prompt.yaml
-├── .data
-│         ├── example
-│         │         └── LogisticsCallCenterConversation.mp3
-│         └── input
-├── .db
-│         └── Callytics.sqlite
-├── .docs
-│         ├── documentation
-│         │         ├── CONTRIBUTING.md
-│         │         └── RESOURCES.md
-│         └── img
-│             ├── Callytics.drawio
-│             ├── Callytics.gif
-│             ├── CallyticsIcon.png
-│             ├── Callytics.png
-│             ├── Callytics.svg
-│            └── database.png
-├── .env
-├── environment.yaml
-├── .gitattributes
-├── .github
-│         └── CODEOWNERS
-├── .gitignore
-├── LICENSE
-├── main.py
-├── README.md
-├── requirements.txt
-└── src
-    ├── audio
-    │         ├── alignment.py
-    │         ├── analysis.py
-    │         ├── effect.py
-    │         ├── error.py
-    │         ├── io.py
-    │         ├── metrics.py
-    │         ├── preprocessing.py
-    │         ├── processing.py
-    │         └── utils.py
-    ├── db
-    │         ├── manager.py
-    │         └── sql
-    │             ├── AudioPropertiesInsert.sql
-    │             ├── Schema.sql
-    │             ├── TopicFetch.sql
-    │             ├── TopicInsert.sql
-    │             └── UtteranceInsert.sql
-    ├── text
-    │         ├── llm.py
-    │         ├─��� model.py
-    │         ├── prompt.py
-    │         └── utils.py
-    └── utils
-        └── utils.py
-19 directories, 43 files
-```
----
-### Database Structure
-![Database Diagram](.docs/img/database.png)
----
-### Version Control System
-##### Releases
-- [v1.0.0](https://github.com/bunyaminergen/Callytics/archive/refs/tags/v1.0.0.zip) _.zip_
-- [v1.0.0](https://github.com/bunyaminergen/Callytics/archive/refs/tags/v1.0.0.tar.gz) _.tar.gz_
-- [v1.1.0](https://github.com/bunyaminergen/Callytics/archive/refs/tags/v1.1.0.zip) _.zip_
-- [v1.1.0](https://github.com/bunyaminergen/Callytics/archive/refs/tags/v1.1.0.tar.gz) _.tar.gz_
-##### Branches
-- [main](https://github.com/bunyaminergen/Callytics/tree/main)
-- [develop](https://github.com/bunyaminergen/Callytics/tree/develop)
----
-### Upcoming
-- [ ] **Speech Emotion Recognition:** Develop a model to automatically detect emotions from speech data.
-- [ ] **New Forced Alignment Model:** Train a forced alignment model from scratch.
-- [ ] **New Vocal Separation Model:** Train a vocal separation model from scratch.
-- [ ] **Unit Tests:** Add a comprehensive unit testing script to validate functionality.
-- [ ] **Logging Logic:** Implement a more comprehensive and structured logging mechanism.
-- [ ] **Warnings:** Add meaningful and detailed warning messages for better user guidance.
-- [ ] **Real-Time Analysis:** Enable real-time analysis capabilities within the system.
-- [ ] **Dockerization:** Containerize the repository to ensure seamless deployment and environment consistency.
-- [ ] **New Transcription Models:** Integrate and test new transcription models
-  suchas [AIOLA’s Multi-Head Speech Recognition Model](https://venturebeat.com/ai/aiola-drops-ultra-fast-multi-head-speech-recognition-model-beats-openai-whisper/).
-- [ ] **Noise Reduction Model:** Identify, test, and integrate a deep learning-based noise reduction model. Consider
-  existing models like **Facebook Research Denoiser**, **Noise2Noise**, **Audio Denoiser CNN**. Write test scripts for
-  evaluation, and if necessary, train a new model for optimal performance.
-##### Considerations
-- [ ] Detect CSR's identity via Voice Recognition/Identification instead of Diarization and LLM.
-- [ ] Transform the code structure into a pipeline for better modularity and scalability.
-- [ ] Publish the repository as a Python package on **PyPI** for wider distribution.
-- [ ] Convert the repository into a Linux package to support Linux-based systems.
-- [ ] Implement a two-step processing workflow: perform **diarization** (speaker segmentation) first, then apply *
-  *transcription** for each identified speaker separately. This approach can improve transcription accuracy by
-  leveraging speaker separation.
-- [ ] Enable **parallel processing** for tasks such as diarization, transcription, and model inference to improve
-  overall system performance and reduce processing time.
-- [ ] Explore using **Docker Compose** for multi-container orchestration if required.
-- [ ] Upload the models and relevant resources to **Hugging Face** for easier access, sharing, and community
-  collaboration.
-- [ ] Consider writing a **Command Line Interface (CLI)** to simplify user interaction and improve usability.
-- [ ] Test the ability to use **different language models (LLMs)** for specific tasks. For instance, using **BERT** for
-  profanity detection. Evaluate their performance and suitability for different use cases as a feature.
----
-### Documentations
-- [RESOURCES](.docs/documentation/RESOURCES.md)
-- [CONTRIBUTING](.docs/documentation/CONTRIBUTING.md)
-- [PRESENTATION](.docs/presentation/CallyticsPresentationEN.pdf)
----
-### Licence
-- [LICENSE](LICENSE)
----
-### Links
-- [Github](https://github.com/bunyaminergen/Callytics)
-- [Website](https://bunyaminergen.com)
-- [Linkedin](https://www.linkedin.com/in/bunyaminergen)
----
-### Team
-- [Bunyamin Ergen](https://www.linkedin.com/in/bunyaminergen)
----
-### Contact
-- [Mail](mailto:[email protected])
----
-### Citation
-```bibtex
-@software{       Callytics,
-  author       = {Bunyamin Ergen},
-  title        = {{Callytics}},
-  year         = {2024},
-  month        = {12},
-  url          = {https://github.com/bunyaminergen/Callytics},
-  version      = {v1.1.0},
-}
-```
----

app.py CHANGED Viewed

@@ -21,7 +21,6 @@ from src.audio.processing import AudioProcessor, Transcriber, PunctuationRestore
 from src.text.utils import Annotator
 from src.text.llm import LLMOrchestrator, LLMResultHandler
 from src.utils.utils import Cleaner
-from src.db.manager import Database
 async def main(audio_file_path: str):
@@ -48,11 +47,6 @@ async def main(audio_file_path: str):
     srt_output_path = ".temp/output.srt"
     config_path = "config/config.yaml"
     prompt_path = "config/prompt.yaml"
-    db_path = ".db/Callytics.sqlite"
-    db_topic_fetch_path = "src/db/sql/TopicFetch.sql"
-    db_topic_insert_path = "src/db/sql/TopicInsert.sql"
-    db_audio_properties_insert_path = "src/db/sql/AudioPropertiesInsert.sql"
-    db_utterance_insert_path = "src/db/sql/UtteranceInsert.sql"
     # Configuration
     config = OmegaConf.load(config_path)
@@ -73,7 +67,6 @@ async def main(audio_file_path: str):
     llm_result_handler = LLMResultHandler()
     cleaner = Cleaner()
     formatter = Formatter()
-    db = Database(db_path)
     audio_feature_extractor = Audio(audio_file_path)
     # Step 1: Detect Dialogue
@@ -165,7 +158,12 @@ async def main(audio_file_path: str):
     annotator.add_conflict(conflict_result)
     # Step 14: Topic Detection
-    topics = db.fetch(db_topic_fetch_path)
     topic_result = await llm_handler.generate(
         "TopicDetection",
         user_input=ssm,
@@ -173,106 +171,16 @@ async def main(audio_file_path: str):
     )
     annotator.add_topic(topic_result)
-    # Step 15: File/Audio Feature Extraction
-    props = audio_feature_extractor.properties()
-    (
-        name,
-        file_extension,
-        absolute_file_path,
-        sample_rate,
-        min_frequency,
-        max_frequency,
-        audio_bit_depth,
-        num_channels,
-        audio_duration,
-        rms_loudness,
-        final_features
-    ) = props
-    rms_loudness_db = final_features["RMSLoudness"]
-    zero_crossing_rate_db = final_features["ZeroCrossingRate"]
-    spectral_centroid_db = final_features["SpectralCentroid"]
-    eq_20_250_db = final_features["EQ_20_250_Hz"]
-    eq_250_2000_db = final_features["EQ_250_2000_Hz"]
-    eq_2000_6000_db = final_features["EQ_2000_6000_Hz"]
-    eq_6000_20000_db = final_features["EQ_6000_20000_Hz"]
-    mfcc_values = [final_features[f"MFCC_{i}"] for i in range(1, 14)]
     final_output = annotator.finalize()
-    # Step 16: Total Silence Calculation
     stats = SilenceStats.from_segments(final_output["ssm"])
     t_std = stats.threshold_std(factor=0.99)
     final_output["silence"] = t_std
     print("Final_Output:", final_output)
-    # Step 17: Database
-    # Step 17.1: Insert File Table
-    summary = final_output.get("summary", "")
-    conflict_flag = 1 if final_output.get("conflict", False) else 0
-    silence_value = final_output.get("silence", 0.0)
-    detected_topic = final_output.get("topic", "Unknown")
-    topic_id = db.get_or_insert_topic_id(detected_topic, topics, db_topic_insert_path)
-    params = (
-        name,
-        topic_id,
-        file_extension,
-        absolute_file_path,
-        sample_rate,
-        min_frequency,
-        max_frequency,
-        audio_bit_depth,
-        num_channels,
-        audio_duration,
-        rms_loudness_db,
-        zero_crossing_rate_db,
-        spectral_centroid_db,
-        eq_20_250_db,
-        eq_250_2000_db,
-        eq_2000_6000_db,
-        eq_6000_20000_db,
-        *mfcc_values,
-        summary,
-        conflict_flag,
-        silence_value
-    )
-    last_id = db.insert(db_audio_properties_insert_path, params)
-    print(f"Audio properties inserted successfully into the File table with ID: {last_id}")
-    # Step 17.2: Insert Utterance Table
-    utterances = final_output["ssm"]
-    for utterance in utterances:
-        file_id = last_id
-        speaker = utterance["speaker"]
-        sequence = utterance["index"]
-        start_time = utterance["start_time"] / 1000.0
-        end_time = utterance["end_time"] / 1000.0
-        content = utterance["text"]
-        sentiment = utterance["sentiment"]
-        profane = 1 if utterance["profane"] else 0
-        utterance_params = (
-            file_id,
-            speaker,
-            sequence,
-            start_time,
-            end_time,
-            content,
-            sentiment,
-            profane
-        )
-        db.insert(db_utterance_insert_path, utterance_params)
-    print("Utterances inserted successfully into the Utterance table.")
-    # Step 18: Clean Up
     cleaner.cleanup(temp_dir, audio_file_path)
     return final_output
@@ -314,4 +222,4 @@ with gr.Blocks() as demo:
     )
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860)

 from src.text.utils import Annotator
 from src.text.llm import LLMOrchestrator, LLMResultHandler
 from src.utils.utils import Cleaner
 async def main(audio_file_path: str):
     srt_output_path = ".temp/output.srt"
     config_path = "config/config.yaml"
     prompt_path = "config/prompt.yaml"
     # Configuration
     config = OmegaConf.load(config_path)
     llm_result_handler = LLMResultHandler()
     cleaner = Cleaner()
     formatter = Formatter()
     audio_feature_extractor = Audio(audio_file_path)
     # Step 1: Detect Dialogue
     annotator.add_conflict(conflict_result)
     # Step 14: Topic Detection
+    topics = [
+        "Complaint",
+        "Technical Support",
+        "Billing",
+        "Order Status",
+    ]
     topic_result = await llm_handler.generate(
         "TopicDetection",
         user_input=ssm,
     )
     annotator.add_topic(topic_result)
     final_output = annotator.finalize()
+    # Step 15: Total Silence Calculation
     stats = SilenceStats.from_segments(final_output["ssm"])
     t_std = stats.threshold_std(factor=0.99)
     final_output["silence"] = t_std
     print("Final_Output:", final_output)
+    # Step 16: Clean Up
     cleaner.cleanup(temp_dir, audio_file_path)
     return final_output
     )
 if __name__ == "__main__":
+    demo.launch()

automation/service/callytics.service DELETED Viewed

@@ -1,19 +0,0 @@
-[Unit]
-Description=Callytics
-After=network.target
-[Service]
-Type=simple
-User=bunyamin
-EnvironmentFile=/home/bunyamin/Callytics/.env
-WorkingDirectory=/home/bunyamin/Callytics
-ExecStart=/bin/bash -c "source /home/bunyamin/anaconda3/etc/profile.d/conda.sh \
-  && conda activate Callytics \
-  && python /home/bunyamin/Callytics/main.py"
-Restart=on-failure
-RestartSec=5
-StandardOutput=journal
-StandardError=journal
-[Install]
-WantedBy=multi-user.target

environment.yaml DELETED Viewed

@@ -1,31 +0,0 @@
-name: Callytics
-channels:
-  - defaults
-  - conda-forge
-dependencies:
-  - python=3.11
-  - pip:
-      - cython==3.0.11
-      - nemo_toolkit[asr]>=2.dev
-      - nltk==3.9.1
-      - faster-whisper==1.1.0
-      - demucs==4.0.1
-      - deepmultilingualpunctuation @ git+https://github.com/oliverguhr/deepmultilingualpunctuation.git@5a0dd7f4fd56687f59405aa8eba1144393d8b74b
-      - ctc-forced-aligner @ git+https://github.com/MahmoudAshraf97/ctc-forced-aligner.git@c7cc7ce609e5f8f1f553fbd1e53124447ffe46d8
-      - openai==1.57.0
-      - accelerate>=0.26.0
-      - torch==2.5.1
-      - pydub==0.25.1
-      - omegaconf==2.3.0
-      - python-dotenv==1.0.1
-      - transformers==4.47.0
-      - librosa==0.10.2.post1
-      - soundfile==0.12.1
-      - noisereduce==3.0.3
-      - numpy==1.26.4
-      - pyannote.audio==3.3.2
-      - watchdog==6.0.0
-      - scipy==1.14.1
-      - IPython==8.30.0
-      - pyyaml==6.0.2
-      - MPSENet==1.0.3