Skip to main content
Version: 3.5.0

Phonexia Enhanced Speech to Text Built on Whisper changelog

1.7.1 (2024-12-11)​

Fixed​

  • [PLAT-978] Loading configuarion from model

Changed​

  • [PLAT-389] Start and end request's messages are logged at the INFO level

1.7.0 (2024-10-01)​

Added​

  • [PLAT-743] Upgraded CTranslate2 to v4

Fixed​

  • [PLAT-936] Crash when using negative values in time range

1.6.0 (2024-09-12)​

Added​

  • [PLAT-888] Added PHX_KEEPALIVE_TIME_S and PHX_KEEPALIVE_TIMEOUT_S options for connection timeout specification

1.5.0 (2024-08-05)​

Changed​

  • [PLAT-801] If set, start_time is added up to all segment timestamps
  • [PLAT-838] Possibility to set beam size on start
  • [PLAT-813] Language tags are case insensitive now

1.4.0 (2024-07-11)​

Added​

  • [PLAT-772] Support for sending RAW audio data
  • [PLAT-781] Support for license extensions

Fixed​

  • [PLAT-758] Device is logged as a number rather than a string

1.3.0 (2024-06-25)​

Added​

  • [PLAT-644] Support for distilled whisper v3 models

1.2.5 (2024-06-06)​

Fixed​

  • [PLAT-788] Missing entrypoint in GPU docker image

1.2.4 (2024-05-30)​

Fixed​

  • [PLAT-756] Inconsistent transcription behavior between autodetect and forced language mode
  • [PLAT-766] Misleading warning message in Python client
  • [PLAT-765] Python client is not compatible with Python 3.8
  • [PLAT-774] Optimized docker images

1.2.3 (2024-05-13)​

Fixed​

  • [PLAT-751] Crash when second request arrive while processing is running

1.2.2 (2024-04-30)​

Fixed​

  • [PLAT-748] Some licenses may be refused by the service

1.2.1 (2024-04-29)​

Fixed​

  • Missing package in pypi

1.2.0 (2024-04-25)​

Added​

  • [PLAT-309] Machine translation
  • [PLAT-669] Support for custom log tags in metadata and logs

Changed​

  • [VOX-667] Renamed microservice to enhanced-speech-to-text-built-on-whisper

1.1.0 (2024-02-21)​

Added​

  • [PLAT-465] Parameters for selecting the part of the audio to process in TranscribeRequest (audio.time_range)
  • [PLAT-581] Parameter for enabling language switching during the transcription in TranscribeRequest (config.enable_language_switching)
  • [PLAT-603] Premature processing cancellation if connection is canceled by client
  • [PLAT-625] Additional logging when initializing service

Fixed​

  • [PLAT-614] Inconsistent license logging

1.0.1 (2024-02-07)​

Fixed​

  • [PLAT-609] Memory access violations

1.0.0 (2024-01-22)​

Added​

  • [PLAT-521] Support for large-v3 Whisper model
  • [VOX-396] Limiting of supported languages for Whisper models
  • [PLAT-520] Correlation ID to log messages
  • [PLAT-439] Optimization to model loading
  • [PLAT-296] Phonexia Voice Activity Detection