…good CPU utilization Virtual machines should be configured after careful consideration about performance RAM speed is more important than CPU clock frequency Because large amounts of data (statistical models) are loaded to RAM, the pipe bandwidth between RAM and CPU is IMPORTANT L3 cache (shared between CPU cores) is a key player. TIP: For best CPU utilization on a single…
Search: cpu
19 results
…VT features can’t help in performance) Also seek for CPUs with a large L3 cache. And the better CPUs are those with higher l3_cache_size/#_of_physical_CPU_cores ratio. We currently assume that CPUs from the current Intel Xeon Family in the 4th generation are the best. For small computation tasks, i7 family CPUs also have reasonable price/performance ratio) Big challenge: correct SPE3/Speech platform…
…CPU cores in the server. Example: Czech STT on stream is approx. 4 times faster than realtime, i.e. 1 CPU core can process 4 realtime streams simultaneously. So a server with 8 CPU cores running only STT stream can be configured as follows: keep 1 core dedicated for operating system and SPE remaining 7 cores can handle 28 realtime workers…
…was detected with 8 SID4 instances using 8 physical CPU cores on a single CPU Under those conditions we can measure total system performance 1200 FTRT when single CPU is used CPU Hyper Threading feature doesn’t bring any performance improvement for SID4 The following data visualization shows performance of the Phonexia SID4 on specific CPU family and its type. Explanation…
…set number of workers and RTP input streams limit automatically New: Added “Settings Adviser” feature, which checks technologies and workers configuration against current CPU and eventually suggests (in log messages) changes for optimal performance New: Added 6th generation of ZH_CN STT, KWS and PHNREC (with features of CS_CZ_6: new VAD generation, dynamic adding of words in preferred phrases, increased transcription…
…for automatic detection server.technology_multithread_initialization.n_threads = Sets the number of parallel threads to be used for technologies initialization. It is a complementary setting to server.technology_multithread_initialization. Default value is 0, which means that the number of threads will be set automatically to number of CPU cores. NOTE: The system needs to read various files of various sizes from the BSAPI location during…
…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…
…1 CPU core (eg. standard 8 CPU core server (8 instances of STT) can process 1010 hours of audio in 1 day of computing time (flat load, depend on technology model)) Supported languages: List of supported languages. Acoustic models Acoustic model is created by training on training data. It includes characteristics of a voices of a set of speakers provided…
…Typical recommended usage: project production stages sharing license between developers demonstration purposes (travelling) HW license HW license is specified by USE_HW line in the license file (the SERVER line is ignored in this case, no Internet connection is required). This license is bound to a “HW profile” of a specific machine (based on OS, CPU, RAM, HDD, ETH). HW…
…of bits used by the waveform absolute value if less than 8, the signal has insufficient quality wfilter_technical_signal_length – the length of technical signals (tones, wide-band noise, etc.), measured in seconds Processing speed Approx. 2,000x faster than real-time processing on 1 CPU core i.e. standard 8 CPU core server processes 384,000 hours of audio in 1 day of computing time…
…coding), A-law or Mu-law, PCM, 8kHz+ sampling Voiceprints: AGE L4 model supports SID4 L4 voiceprints; legacy AGE models support voiceprints created by AGE itself Output Log file with processed information (age estimate) Processing speed Approx. 20x faster than real-time processing on 1 CPU core i.e. standard 8 CPU core server processes 3,840 hours of audio in 1 day of computing…
…models VIN application (graphical user interface, GUI) with the following technologies in-build Speaker Identification (SID4_XL5) Speaker Diarization (DIAR) Voice Activity Detection (VAD) Speech Quality Estimator (SQE) Phoneme Recogniser (PHNREC) example population sets and audio (in ./examples/) and example report templates (in ./templates/) Hardware requirements minimum – CPU: Intel® Core™ i5, RAM: 4 GB, Required HDD space: 0.5 GB for software…
…product executable file “properties” files (phxspe.properties from SPE is minimum) – usually in ./settings/ directory Issue data – supporting: Actual and active HW configuration (CPU, OS, RAM, storage status (free space)), you might use the following to get the information: The Benchmark function in SPE or Phonexia’s hw-gen for generating basic HW print Windows 64bit http://download.phonexia.com/utils/hw-gen64.exe GNU/Linux 64bit http://download.phonexia.com/utils/hw-gen64 System…
…technological model and can range from 5 to 50 times faster than real time on 1 server CPU core. Voiceprint extraction is the most time-consuming part of the process. Voiceprint comparison, on the other hand, is extremely fast – a millions of voiceprint comparisons can be done in 1 second. Voiceprint extraction (Speaker enrollment) Speaker enrollment starts with the extraction…
…based on C++11/14 and metaprogramming Copyright: 2010-2017 Sebastien Andrivet blaze BSD-3-Clause boost BSL-1.0 botan BSD-2-Clause bzip2 bzip2-1.0.8 cpp-httplib MIT dlfcn-win32 (Windows only) LGPL duktape MIT (https://github.com/svaarala/duktape/blob/master/LICENSE.txt) – Connect your Github account flac BSD-style license fmt MIT gsl-lite MIT libbacktrace (Linux only) BSD-3-Clause libcpuid GitHub – anrieff/libcpuid: a small C library for x86 CPU detection and feature extraction mariadb-connector-c LGPL-2.1-or-later minizip…