Skip to content
Projekte

ronitgupta138/Vox-Intel-Engine

Auf GitHub ansehen

ronitgupta138/Vox-Intel-Engine has 45 GitHub stars and 1 forks. Star changes are not measured yet. Last checked 2026-11-08 19:07 UTC. Last push 2026-11-05.

So werden diese Zahlen gemessen

๐ŸŽ™๏ธ Real-Time Multi-Modal Speech Telemetry & Acoustic DSP Engine (FastAPI, Python 3.11, Autocorrelation Pitch, FFT Spectral Energy & Lexical Pacing Analytics).

45 Sterne1 forks

What you can do

  • Fundamental Frequency ($F_0$): Normalized autocorrelation over Fourier transform frames estimating vocal pitch register ($75 ext{ Hz} - 500 ext{ Hz}$).
  • Intonation Variety & Pitch Jitter ($\sigma_{F_0}$): Measures standard deviation around mean pitch to detect flat/monotone delivery vs expressive presentation style.
  • Root Mean Square (RMS) Volume Dynamics: Decibel-scale loudness measurement ($20 \log_{10}( ext{RMS})$) and peak-to-floor dynamic contrast.
  • Micro-Pause Segmentation: Automated detection of hesitation gaps ($>300 ext{ms}$) vs natural rhythmic pauses.

Gemessener Sternzuwachs

in 24h
Aktualisierung verzรถgert
in 7 days
Aktualisierung verzรถgert
in 15 days
Aktualisierung verzรถgert
in 1 month
Aktualisierung verzรถgert

Nettoรคnderungen in รผberlappenden Zeitrรคumen, keine Tagessummen. Fehlende Messwerte bleiben leer. Sterne zeigen Interesse, nicht Qualitรคt.

README.md

Original 
โ–ˆโ–ˆโ•—   โ–ˆโ–ˆโ•— โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ•— โ–ˆโ–ˆโ•—  โ–ˆโ–ˆโ•—  โ–ˆโ–ˆโ•—โ–ˆโ–ˆโ–ˆโ•—   โ–ˆโ–ˆโ•—โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ•—โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ•—โ–ˆโ–ˆโ•—     
โ–ˆโ–ˆโ•‘   โ–ˆโ–ˆโ•‘โ–ˆโ–ˆโ•”โ•โ•โ•โ–ˆโ–ˆโ•—โ•šโ–ˆโ–ˆโ•—โ–ˆโ–ˆโ•”โ•  โ–ˆโ–ˆโ•‘โ–ˆโ–ˆโ–ˆโ–ˆโ•—  โ–ˆโ–ˆโ•‘โ•šโ•โ•โ–ˆโ–ˆโ•”โ•โ•โ•โ–ˆโ–ˆโ•”โ•โ•โ•โ•โ•โ–ˆโ–ˆโ•‘     
โ–ˆโ–ˆโ•‘   โ–ˆโ–ˆโ•‘โ–ˆโ–ˆโ•‘   โ–ˆโ–ˆโ•‘ โ•šโ–ˆโ–ˆโ–ˆโ•”โ•   โ–ˆโ–ˆโ•‘โ–ˆโ–ˆโ•”โ–ˆโ–ˆโ•— โ–ˆโ–ˆโ•‘   โ–ˆโ–ˆโ•‘   โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ•—  โ–ˆโ–ˆโ•‘     
โ•šโ–ˆโ–ˆโ•— โ–ˆโ–ˆโ•”โ•โ–ˆโ–ˆโ•‘   โ–ˆโ–ˆโ•‘ โ–ˆโ–ˆโ•”โ–ˆโ–ˆโ•—   โ–ˆโ–ˆโ•‘โ–ˆโ–ˆโ•‘โ•šโ–ˆโ–ˆโ•—โ–ˆโ–ˆโ•‘   โ–ˆโ–ˆโ•‘   โ–ˆโ–ˆโ•”โ•โ•โ•  โ–ˆโ–ˆโ•‘     
 โ•šโ–ˆโ–ˆโ–ˆโ–ˆโ•”โ• โ•šโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ•”โ•โ–ˆโ–ˆโ•”โ• โ–ˆโ–ˆโ•—  โ–ˆโ–ˆโ•‘โ–ˆโ–ˆโ•‘ โ•šโ–ˆโ–ˆโ–ˆโ–ˆโ•‘   โ–ˆโ–ˆโ•‘   โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ•—โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ•—
  โ•šโ•โ•โ•โ•   โ•šโ•โ•โ•โ•โ•โ• โ•šโ•โ•  โ•šโ•โ•  โ•šโ•โ•โ•šโ•โ•  โ•šโ•โ•โ•โ•   โ•šโ•โ•   โ•šโ•โ•โ•โ•โ•โ•โ•โ•šโ•โ•โ•โ•โ•โ•โ•

VoxIntel Engine โ€” Multi-Modal Speech Telemetry & Acoustic DSP Engine (FastAPI & Python 3.11)

GitHub Stars Python FastAPI NumPy Docker CI

๐Ÿ“Œ Architectural Overview

VoxIntel Engine is an asynchronous, high-throughput microservice that analyzes technical presentations, executive pitches, and mock interview speeches across multiple parallel acoustic and semantic streams:

                           [ Audio Stream (WAV/PCM) + Transcript ]
                                              โ”‚
                     โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
                     โ–ผ                                                 โ–ผ
     โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”                 โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
     โ”‚   Acoustic DSP Analyzer       โ”‚                 โ”‚   Lexical NLP Analyzer        โ”‚
     โ”‚ - FFT Fundamental Pitch (F0)  โ”‚                 โ”‚ - Words Per Minute (WPM)      โ”‚
     โ”‚ - RMS Energy & Volume (dB)    โ”‚                 โ”‚ - Filler Word Density         โ”‚
     โ”‚ - Silence / Hesitation Pauses โ”‚                 โ”‚ - Type-Token Ratio (TTR)      โ”‚
     โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜                 โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
                     โ”‚                                                 โ”‚
                     โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
                                              โ”‚
                                              โ–ผ
                             โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
                             โ”‚   Multi-Modal Fusion Engine     โ”‚
                             โ”‚ - Calibrated Scoring Matrix     โ”‚
                             โ”‚ - Delivery Grade (A+ to C)      โ”‚
                             โ”‚ - Actionable Coaching Insights  โ”‚
                             โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜

โšก Core Telemetry & Mathematical Capabilities

  1. Acoustic Digital Signal Processing:

    • Fundamental Frequency ($F_0$): Normalized autocorrelation over Fourier transform frames estimating vocal pitch register ($75 ext{ Hz} - 500 ext{ Hz}$).
    • Intonation Variety & Pitch Jitter ($\sigma_{F_0}$): Measures standard deviation around mean pitch to detect flat/monotone delivery vs expressive presentation style.
    • Root Mean Square (RMS) Volume Dynamics: Decibel-scale loudness measurement ($20 \log_{10}( ext{RMS})$) and peak-to-floor dynamic contrast.
    • Micro-Pause Segmentation: Automated detection of hesitation gaps ($>300 ext{ms}$) vs natural rhythmic pauses.

  2. Lexical & NLP Metrics:

    • Speaking Pace (WPM): Classifies cadence against standard presentation benchmarks ($125 - 155 ext{ WPM}$ ideal).
    • Filler Word Density: Regex token analysis detecting common hesitation crutches (um, uh, like, actually, basically, you know).
    • Lexical Diversity (Type-Token Ratio): Vocabulary richness calculation ($TTR = rac{ ext{Unique Tokens}}{ ext{Total Tokens}}$).

  3. Multi-Modal Confidence Matrix:

    • Weighted multi-dimensional scoring evaluating Pacing (25%), Fluency (25%), Vocal Energy (25%), and Intonation (25%) to output an overall calibrated confidence index ($0 - 100$).

๐Ÿ“ก REST API Reference

1. Multi-Modal Audio Analysis

POST /api/v1/analyze/audio (Multipart Form)

  • file: Audio recording (.wav)
  • transcript (optional): Spoken text transcript

2. Transcript-Only Pacing Analysis

POST /api/v1/analyze/text (JSON Body)

{
  "transcript": "Good morning. In this presentation, I will discuss distributed consensus algorithms and our high-throughput transaction architecture.",
  "duration_seconds": 15.0
}

3. Health & Telemetry

GET /api/v1/health

๐Ÿš€ Quick Start (Docker)

git clone https://github.com/ronitgupta138/vox-intel-engine.git
cd vox-intel-engine

# Start service container
docker compose up --build -d

# Interactive Swagger UI available at:
# http://localhost:8000/docs

๐Ÿงช Running Unit Tests

pytest -v tests/

๐Ÿ“œ License

This project is open-source under the MIT License.

ร„hnliche Projekte entdecken

Asabeneh/30-Days-Of-Python

Die Programmier-Challenge 30 Days of Python ist eine Schritt-fรผr-Schritt-Anleitung, um die Programmiersprache Python in 30 Tagen zu lernen. Diese Challenge kann mehr als 100 Tage dauern. Gehe in deinem eigenen Tempo vor. Diese Videos kรถnnen ebenfalls helfen: https://www.youtube.com/channel/UC7PNRuno1rzYPb1xLa4yktw

78,423 Sterne

grafana/grafana

Offene und kombinierbare Plattform fรผr Observability und Datenvisualisierung. Visualisiert Metriken, Logs und Traces aus mehreren Quellen wie Prometheus, Loki, Elasticsearch, InfluxDB, Postgres und vielen weiteren.

77,763 Sterne

redis/redis

Fรผr Entwickler, die echtzeitfรคhige, datengesteuerte Anwendungen erstellen, ist Redis der bevorzugte, schnellste und funktionsreichste Cache, Datenstrukturserver und die entsprechende Abfrageengine fรผr Dokumente und Vektoren.

77,309 Sterne

apache/superset

Apache Superset ist eine Plattform fรผr Datenvisualisierung und Datenexploration.

75,453 Sterne