Skip to main content
Version: 3.6.0

Phonexia Gender Identification changelog

1.3.1 (2025-01-27)​

Added​

  • [PLAT-1074] GPU docker image that accelerates the processing of audio by the GPU

1.3.0 (2025-01-23)​

Added​

  • [PLAT-1073] Support for processing audio files
    • Added arguments --device, --num_threads_per_instance, --num_instances_per_device and --device_index
    • Added to the API: IdentifyRequest.audio, IdentifyRequest.config, IdentifyResponse.processed_audio_length, IdentifyResult.speech_length
  • [PLAT-1070] Default port 8080 exposed in Dockerfile

Changed​

  • IdentifyResult.score_male and IdentifyResult.score_female are optional (they are not set for empty/short audio or voiceprint created from empty/short audio)

1.2.0 (2024-09-16)​

Added​

  • [PLAT-749] Probability to the identification result
  • [PLAT-888] Added PHX_KEEPALIVE_TIME_S and PHX_KEEPALIVE_TIMEOUT_S options for connection timeout specification

1.1.0 (2024-06-03)​

Added​

  • [PLAT-669] Add support for custom log tags in metadata and logs.
  • [PLAT-774] Optimized docker images.

1.0.0 (2024-03-27)​

Added​

  • Gender Identification microservice