Skip to content Skip to main navigation Skip to footer

Download Speech Platform

Step #1 – Download the right package for you

Basic package for desktop (recommended)

This package allows new users to try and evaluate all Phonexia speech technologies easily, either using Phonexia Browser, or directly using Speech Engine (SPE, REST API).

Icon

Phonexia Speech Platform 3.50.4 for Windows 64-bit 3.9 GB

Icon

Phonexia Speech Platform 3.50.4 for Linux 64-bit 3.9 GB

    Content of basic package
    • Speech Engine (SPE v3.50.4) – technologies included:
      • Speech to Text (STT) – model EN_US_6 (US English)
      • Keyword Spotting (KWS) – model EN_US_6 (US English)
      • Speaker Identification 4 (SID4) – model XL4
      • Speaker Diarization (DIAR) – model XL4
      • Language Identification (LID) – model L4
      • Gender Identification (GID) – model XL4
      • Age Estimation (AGE) ) – model L4
      • Voice Activity Detection (VAD) – model GENERIC_3
      • Speech Quality Estimator (SQE)
      • Phoneme Recognizer (PHNREC) – model EN_US_6 (US English)
      • Time Analysis Extraction (TAE)
      • Waveform Denoiser (DENOISER)
    • Phonexia Browser (BROWSER v3.50.1)
    • Reporting and Licensing Server (RLS v0.13.1)
    • example audio
      (in ./BROWSER/example/ and ./SPE/bsapi/{technology}/example/)
    Hardware requirements for basic package

    minimum:

    • CPU: Intel® Core™ i5
    • RAM: 16 GB
    • Storage: 10 GB
      SSD is strongly recommended for superior performance over HDD

    recommended:

    • CPU: Intel® Core™ i7 or better
    • RAM: 32 GB
    • Storage: 10+ GB
      SSD is strongly recommended for superior performance over HDD

    Note: Please see additional information on Recommended OS and HW page for the most common configurations.

     

    Step #2 – First start

    1. Ensure you have obtained license (license.dat).
      To obtain evaluation license, contact your Phonexia sales manager, or ask at [email protected]).
    2. Unzip the downloaded package (ZIP) to a location of your choice (e.g. ~/Phonexia/).
    3. Save the license.dat file to the root of the Speech Platform directory (e.g. ~/Phonexia/).
    4. Run ./run_browser.sh (Linux) or run_browser.cmd (Windows).
    5. Set up wizard will be launched automatically and help you with the first start.
    6. You can use example data included in the ZIP package (located in ./BROWSER/example/).

    Step #3 – Check Documentation and Tutorials