VOSK Speech Recognition Toolkit

VOSK is an open-source offline speech recognition API/toolkit. VOSK supports speech recognition in 17 languages and has a variety of models available and interfaces for different programming languages. This test profile times the speech-to-text process for a roughly three minute audio recording.

To run this test with the Phoronix Test Suite, the basic command is: phoronix-test-suite benchmark vosk.

Project Site

alphacephei.com

Test Created

27 April 2021

Test Maintainer

Michael Larabel 

Test Type

Processor

Average Install Time

22 Seconds

Average Run Time

1 Minute, 24 Seconds

Test Dependencies

Python

Accolades

10k+ Downloads

Supported Platforms


Public Result Uploads *Reported Installs **Reported Test Completions **Test Profile Page ViewsOpenBenchmarking.orgEventsVOSK Speech Recognition Toolkit Popularity Statisticspts/vosk2021.042021.052021.062021.072021.082021.092021.102021.112021.122022.012022.022022.032022.042022.052022.062022.072022.082022.092022.102022.112022.122023.012023.022023.032023.042023.052023.062023.072023.082023.092023.102023.112023.122024.012024.022024.032024.042024.052024.062024.072024.082024.092024.102K4K6K8K10K
* Uploading of benchmark result data to OpenBenchmarking.org is always optional (opt-in) via the Phoronix Test Suite for users wishing to share their results publicly.
** Data based on those opting to upload their test results to OpenBenchmarking.org and users enabling the opt-in anonymous statistics reporting while running benchmarks from an Internet-connected platform.
Data updated weekly as of 5 October 2024.

Revision History

pts/vosk-1.0.1   [View Source]   Tue, 27 Apr 2021 14:09:26 GMT
Set python external dependency.

pts/vosk-1.0.0   [View Source]   Tue, 27 Apr 2021 14:06:19 GMT
Initial commit of VOSK.

Suites Using This Test

Creator Workloads

Speech

Telephony


Performance Metrics

Analyze Test Configuration:

VOSK Speech Recognition Toolkit 0.3.21

OpenBenchmarking.org metrics for this test profile configuration based on 445 public results since 27 April 2021 with the latest data as of 26 August 2024.

Below is an overview of the generalized performance for components where there is sufficient statistically significant data based upon user-uploaded results. It is important to keep in mind particularly in the Linux/open-source space there can be vastly different OS configurations, with this overview intended to offer just general guidance as to the performance expectations.

Component
Percentile Rank
# Compatible Public Results
Seconds (Average)
100th
7
11.5 +/- 0.1
96th
6
12.4 +/- 0.2
96th
6
12.5 +/- 0.2
96th
8
12.5 +/- 0.2
91st
10
13.9 +/- 0.3
87th
8
14.4 +/- 0.4
86th
7
14.5 +/- 0.1
83rd
9
14.6 +/- 0.1
82nd
16
14.9 +/- 0.9
80th
8
15.3 +/- 0.3
76th
4
16.0 +/- 0.1
Mid-Tier
75th
> 16.0
73rd
5
16.4 +/- 0.3
72nd
3
16.6 +/- 0.1
67th
13
17.1 +/- 0.3
67th
7
17.1 +/- 1.3
67th
3
17.1 +/- 0.7
66th
3
17.1 +/- 0.2
66th
3
17.2 +/- 0.3
64th
3
17.5 +/- 0.3
63rd
3
17.6 +/- 0.1
60th
3
18.0 +/- 1.2
56th
10
19.1 +/- 0.9
54th
3
19.6 +/- 0.2
51st
3
20.1 +/- 0.3
Median
50th
20.1
50th
3
20.2 +/- 0.1
49th
4
20.2 +/- 0.2
49th
3
20.3 +/- 0.1
46th
4
20.4 +/- 0.1
45th
3
20.5 +/- 0.1
44th
10
20.6 +/- 0.3
44th
3
20.6 +/- 0.1
41st
4
20.9 +/- 0.1
40th
3
21.0 +/- 0.1
36th
4
21.5 +/- 0.1
35th
10
21.6 +/- 0.2
33rd
3
22.2 +/- 0.1
32nd
4
22.2 +/- 0.1
30th
10
22.4 +/- 0.3
29th
6
22.6 +/- 0.1
29th
3
22.6 +/- 0.1
27th
3
22.7 +/- 0.4
26th
3
22.9 +/- 0.1
Low-Tier
25th
> 22.9
22nd
4
23.8 +/- 0.1
21st
6
23.9 +/- 0.2
20th
3
24.1 +/- 1.4
19th
4
24.6 +/- 0.1
18th
5
24.7 +/- 0.2
16th
4
24.9 +/- 0.1
16th
3
25.0 +/- 0.7
15th
3
25.0 +/- 0.1
12th
8
26.2 +/- 0.3
11th
3
26.6 +/- 0.2
10th
3
27.2 +/- 0.1
8th
3
28.3 +/- 1.4
8th
3
28.4 +/- 1.5
7th
3
28.6 +/- 1.6
6th
3
29.4 +/- 0.4
5th
4
30.9 +/- 2.4
3rd
3
37.0 +/- 0.1
2nd
3
37.8 +/- 0.2
1st
3
44.9 +/- 0.7
OpenBenchmarking.orgDistribution Of Public Results445 Results Range From 11 To 46 Seconds11141720232629323538414447306090120150

Based on OpenBenchmarking.org data, the selected test / test configuration (VOSK Speech Recognition Toolkit 0.3.21) has an average run-time of 2 minutes. By default this test profile is set to run at least 3 times but may increase if the standard deviation exceeds pre-defined defaults or other calculations deem additional runs necessary for greater statistical accuracy of the result.

OpenBenchmarking.orgMinutesTime Required To Complete BenchmarkRun-Time246810Min: 1 / Avg: 1.31 / Max: 5

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 0.4%.

OpenBenchmarking.orgPercent, Fewer Is BetterAverage Deviation Between RunsDeviation246810Min: 0 / Avg: 0.44 / Max: 4

Does It Scale Well With Increasing Cores?

No, based on the automated analysis of the collected public benchmark data, this test / test settings does not generally scale well with increasing CPU core counts. Data based on publicly available results for this test / test settings, separated by vendor, result divided by the reference CPU clock speed, grouped by matching physical CPU core count, and normalized against the smallest core count tested from each vendor for each CPU having a sufficient number of test samples and statistically significant data.

IntelAMDOpenBenchmarking.orgRelative Core Scaling To BaseVOSK Speech Recognition Toolkit CPU Core Scaling24681216640.38960.77921.16881.55841.948

Tested CPU Architectures

This benchmark has been successfully tested on the below mentioned architectures. The CPU architectures listed is where successful OpenBenchmarking.org result uploads occurred, namely for helping to determine if a given test is compatible with various alternative CPU architectures.

CPU Architecture
Kernel Identifier
Verified On
Intel / AMD x86 64-bit
x86_64
(Many Processors)

Recent Test Results

OpenBenchmarking.org Results Compare

1 System - 377 Benchmark Results

AMD Ryzen 7 5800X 8-Core - ASUS ROG STRIX X370-F GAMING - AMD Starship

Linuxmint 21.3 - 6.5.0-35-lowlatency - X Server 1.21.1.4

Find More Test Results