Recommended OS and HW (PSP)
Recommended operating systems
- Windows 64-bit – Windows Server 2019 (*), latest version of Windows 10 (*)
- Linux 64-bit – latest version of RHEL/CentOS 7 (*)
since version 3.62: latest version of RHEL/Rocky Linux/Alma Linux 8
Compatible Operating Systems (**) :
- 64-bit Windows 8.1, Windows Server 2016, and newer
- 64-bit Linux with glibc >= 2.17, e.g. Ubuntu 20.04, Mint 19.3, RHEL/CentOS 8.2, …
since version 3.62: 64-bit Linux with glibc >= 2.28, e.g. Ubuntu 20.04, Linux Mint 4-LMDE, RHEL/Rocky Linux/AlmaLinux 8
(*) Speech Platform components (e.g. Speech Engine) are tested by Phonexia on these systems.
(**) Speech Platform components (e.g. Speech Engine) are known to be successfully deployed on these systems.
Recommended hardware
Required HW resources depend on set of technologies (i.e. SPE configuration) and the load that should be processed per day (or during a peak hour). Additionally, your own application built on top of SPE (including eventual external dependencies like databases, storages, etc.) would require additional resources. Therefore you should always perform a proper load test using your entire system to determine the actual HW requirements.
To give you a picture, here are recommendations for typical configurations:
Voice Biometrics, basic 100 hours/day package (***) files processing
- CPU: 8 physical cores, 1x Intel® Xeon E5-2640 v4 or similar or 10th Gen Intel® Core Processor
- RAM: 16 GB
- Storage: 100 GB (depends on audio retention policy)
SSD strongly recommended for superior performance over HDD - Configuration includes: SID4 XL4, GID XL4, LID L4, AGE L4, VAD, SQE
Transcription System, basic 100 hours/day package (***) files processing
- CPU: 8 physical cores, 1x Intel® Xeon E5-2640 v4 or similar or 10th Gen Intel® Core Processor
- RAM: 16 GB
- Storage: 100 GB (depends on your audio retention policy)
SSD strongly recommended for superior performance over HDD - Configuration includes: STT 6th generation – 2 languages (half load each), KWS 6th generation – 2 languages, LID L4, VAD, SQE
Voice Biometrics + Transcription System, basic 100 hours/day package (***) files processing
- CPU: 14 physical cores, 1x Intel® Xeon Gold 5120 or similar or 10th Gen Intel® Core Processor
- RAM: 32 GB
- Storage: 500 GB (depends on your audio retention policy)
SSD strongly recommended for superior performance over HDD - Configuration includes: SID4 XL4, GID XL4, LID L4, AGE L4, STT 6th generation – 2 languages (half load each), KWS 6th generation – 2 languages, VAD, SQE
(***) The amount of hours/day refers to the Phonexia pricing package, it does NOT mean maximum throughput of such configuration. In other words, this is recommended configuration, not minimal configuration.