DeepSpeech

Mozilla DeepSpeech is a speech-to-text engine powered by TensorFlow for machine learning and derived from Baidu's Deep Speech research paper. 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 deepspeech.

Project Site

github.com

Test Created

8 December 2019

Last Updated

8 December 2019

Test Maintainer

Michael Larabel 

Test Type

Processor

Average Install Time

17 Seconds

Average Run Time

5 Minutes, 32 Seconds

Accolades

5k+ Downloads

Supported Platforms

Supported Architectures

x86_64
Public Result UploadsReported Installs*Test Completions*OpenBenchmarking.orgEventsDeepSpeech Popularity Statisticspts/deepspeech2019.122020.012020.022020.032020.042020.052020.062020.072020.082020.092020.102020.112020.122021.012021.022021.032021.042004006008001000
* 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 current as of Fri, 09 Apr 2021 23:31:52 GMT.

Revision History

pts/deepspeech-1.0.0   [View Source]   Sun, 08 Dec 2019 12:41:29 GMT
Initial commit of Mozilla DeepSpeech

Suites Using This Test

Machine Learning

Creator Workloads

HPC - High Performance Computing

Single-Threaded

Speech


Performance Metrics

Analyze Test Configuration:

DeepSpeech 0.6

Acceleration: CPU

OpenBenchmarking.org metrics for this test profile configuration based on 1,226 public results since 8 December 2019 with the latest data as of 7 April 2021.

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
# Matching Public Results
Seconds (Average)
AMD Ryzen 3 3300X 4-Core
99th
3
53
AMD Ryzen 5 5600X 6-Core
99th
14
53 +/- 4
AMD Ryzen 3 3100 4-Core
98th
3
55
AMD Ryzen Threadripper 3970X 32-Core
96th
22
56 +/- 3
AMD Ryzen Threadripper 3960X 24-Core
95th
3
57 +/- 2
AMD Ryzen 9 5900X 12-Core
92nd
33
59 +/- 4
AMD Ryzen 7 5800X 8-Core
92nd
14
59 +/- 7
Intel Core i5-8400
90th
3
60 +/- 1
Intel Core i9-11900K
90th
7
60
AMD Ryzen 5 3600X 6-Core
88th
12
61 +/- 5
AMD Ryzen 9 5950X 16-Core
88th
34
61 +/- 4
AMD Ryzen 7 3700X 8-Core
85th
7
62 +/- 4
AMD Ryzen Threadripper 3990X 64-Core
85th
14
62 +/- 4
AMD Ryzen 9 3900XT 12-Core
84th
16
63 +/- 2
AMD Ryzen 7 3800X 8-Core
84th
4
63 +/- 7
AMD Ryzen 9 3950X 16-Core
84th
23
63 +/- 2
AMD Ryzen 9 3900X 12-Core
84th
23
63 +/- 6
AMD Ryzen 7 3800XT 8-Core
82nd
11
64 +/- 4
Intel Core i5-6500
77th
12
67 +/- 3
Intel Core i3-8100
77th
5
67 +/- 5
Intel Core i5-9400F
77th
6
67 +/- 1
Mid-Tier
75th
> 68
Intel Core i7-1065G7
75th
11
68 +/- 5
Intel Core i5-10600K
73rd
15
69 +/- 6
Intel Core i7-1165G7
73rd
32
69 +/- 9
Intel Core i7-8700K
73rd
7
69 +/- 1
Intel Core i9-9900K
72nd
3
70 +/- 1
AMD EPYC 7F52 16-Core
72nd
14
70 +/- 3
AMD Ryzen 3 2200G
70th
5
71 +/- 3
Intel Core i9-9900KS
70th
10
71 +/- 2
AMD Ryzen 5 3400G
70th
3
71 +/- 2
AMD EPYC 7F72 24-Core
68th
7
72 +/- 2
AMD EPYC 7F32 8-Core
68th
9
72 +/- 3
AMD Athlon 3000G
66th
11
73 +/- 6
Intel Xeon E3-1270 v5
66th
3
73
2 x AMD EPYC 7542 32-Core
61st
4
75 +/- 2
AMD EPYC 7662 64-Core
60th
8
76 +/- 5
2 x AMD EPYC 7F52 16-Core
60th
6
76 +/- 1
Intel Core i7-9750H
60th
10
76 +/- 4
AMD EPYC 7502P 32-Core
60th
12
76 +/- 5
AMD EPYC 7302P 16-Core
58th
14
77 +/- 4
AMD EPYC 7702 64-Core
58th
20
77 +/- 3
AMD Ryzen 5 2600 Six-Core
58th
3
77 +/- 2
AMD Ryzen 7 4700U
58th
3
77
AMD EPYC 7402P 24-Core
58th
10
77 +/- 5
Intel Xeon E3-1280 v5
57th
4
78 +/- 1
AMD EPYC 7642 48-Core
57th
15
78 +/- 3
AMD EPYC 7552 48-Core
57th
7
78 +/- 4
AMD EPYC 7232P 8-Core
57th
12
78 +/- 4
2 x AMD EPYC 7552 48-Core
57th
4
78 +/- 5
AMD EPYC 7542 32-Core
57th
6
78 +/- 4
AMD EPYC 7502 32-Core
54th
5
79 +/- 4
AMD EPYC 7272 12-Core
54th
5
79 +/- 4
AMD Ryzen 7 1800X Eight-Core
54th
4
79 +/- 2
Intel Core i9-10900K
54th
28
79 +/- 1
AMD EPYC 7532 32-Core
54th
7
79 +/- 4
Intel Core i7-10700T
54th
8
79 +/- 1
AMD EPYC 7452 32-Core
51st
9
80 +/- 4
AMD Ryzen 5 2400G
51st
5
80 +/- 11
Intel Core i9-10885H
51st
8
80 +/- 2
Intel Xeon E3-1245 v5
51st
3
80 +/- 1
AMD Ryzen Threadripper 2970WX 24-Core
51st
3
80 +/- 3
Median
50th
80
AMD EPYC 7262 8-Core
48th
5
81 +/- 5
AMD EPYC 7282 16-Core
48th
8
81 +/- 3
AMD EPYC 7352 24-Core
48th
6
81 +/- 3
AMD Ryzen 5 4500U
48th
15
81 +/- 9
AMD EPYC 7252 8-Core
48th
4
81 +/- 5
AMD Ryzen 7 2700X Eight-Core
44th
6
82 +/- 3
2 x AMD EPYC 7F32 8-Core
41st
5
84 +/- 2
2 x AMD EPYC 7302 16-Core
41st
4
84 +/- 4
2 x AMD EPYC 7502 32-Core
39th
7
87 +/- 12
2 x AMD EPYC 7352 24-Core
38th
7
89 +/- 8
2 x AMD EPYC 7272 12-Core
38th
4
90 +/- 7
2 x AMD EPYC 7282 16-Core
37th
5
91 +/- 6
2 x AMD EPYC 7252 8-Core
37th
5
92 +/- 10
2 x AMD EPYC 7262 8-Core
37th
5
93 +/- 9
Intel Core i5-7600K
37th
3
93 +/- 2
Intel Core i7-8565U
35th
4
95 +/- 2
AMD Ryzen 3 3200U
35th
9
95 +/- 4
Intel Core i3-10110U
35th
4
96 +/- 4
Intel Core i9-7980XE
33rd
12
99 +/- 7
AMD Ryzen 7 1700 Eight-Core
32nd
7
104 +/- 7
2 x Intel Xeon Gold 6258R
31st
4
106 +/- 1
Intel Core i7-8550U
28th
6
109 +/- 11
2 x Intel Xeon Gold 6230R
28th
3
109 +/- 1
Intel Core i7-6800K
26th
7
110 +/- 1
Low-Tier
25th
> 111
Intel Xeon Platinum 8280
23rd
3
115 +/- 6
Intel Core i9-10980XE
23rd
34
115 +/- 7
2 x Intel Xeon Gold 6250
23rd
4
115 +/- 3
2 x Intel Xeon Gold 5220R
22nd
9
116 +/- 8
Intel Core i7-5960X
22nd
5
116 +/- 11
2 x Intel Xeon Silver 4214R
22nd
4
117 +/- 1
Intel Xeon Gold 5217
21st
10
118 +/- 7
2 x Intel Xeon Gold 6226R
21st
3
119 +/- 7
Intel Xeon Gold 5220R
19th
3
121 +/- 8
Intel Xeon Gold 6226R
17th
8
123 +/- 5
2 x AMD EPYC 7601 32-Core
17th
3
123 +/- 10
Intel Xeon Silver 4108
17th
3
124 +/- 2
2 x Intel Xeon Silver 4216
16th
4
125 +/- 10
2 x Intel Xeon Silver 4210R
16th
3
126 +/- 1
2 x Intel Xeon Silver 4210
15th
4
127
2 x Intel Xeon Silver 4215R
15th
4
128 +/- 5
Intel Xeon Silver 4214R
14th
5
129 +/- 8
Intel Core i9-7940X
14th
7
129
Intel Core i7-4960X
14th
4
129 +/- 4
Intel Xeon Gold 5218
14th
13
130 +/- 9
2 x Intel Xeon Platinum 8259L
13th
5
131 +/- 11
Intel Xeon Silver 4216
13th
15
131 +/- 12
2 x Intel Xeon Platinum 8272CL
12th
4
132 +/- 10
Intel Xeon Silver 4215R
11th
5
135 +/- 8
Intel Xeon Platinum 8253
10th
4
137 +/- 9
Intel Core i5-4440S
10th
3
138 +/- 4
Intel Core i7-2700K
10th
17
139 +/- 11
2 x Intel Xeon Gold 6254
5th
29
166 +/- 7
AMD A10-7870K Radeon R7 12 Compute Cores 4C
3rd
3
244 +/- 3
AMD FX-8150 Eight-Core
2nd
4
258 +/- 19
AMD A10-7850K APU
2nd
4
271 +/- 25
AMD FX-8370 Eight-Core
2nd
6
282 +/- 8
AMD FX-8350 Eight-Core
1st
8
292 +/- 4
OpenBenchmarking.orgDistribution Of Public Results - Acceleration: CPU1226 Results Range From 49 To 377 Seconds496785103121139157175193211229247265283301319337355373391100200300400500

Based on OpenBenchmarking.org data, the selected test / test configuration (DeepSpeech 0.6 - Acceleration: CPU) has an average run-time of 4 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 BenchmarkAcceleration: CPURun-Time510152025Min: 1 / Avg: 4.04 / Max: 18

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 0.6%.

OpenBenchmarking.orgPercent, Fewer Is BetterAverage Deviation Between RunsAcceleration: CPUDeviation246810Min: 0 / Avg: 0.59 / Max: 6

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.

AMDIntelOpenBenchmarking.orgRelative Core Scaling To BaseDeepSpeech CPU Core ScalingAcceleration: CPU2468121618243248640.71251.4252.13752.853.5625

Notable Instruction Set Usage

Notable instruction set extensions supported by this test, based on an automatic analysis by the Phoronix Test Suite / OpenBenchmarking.org analytics engine.

Instruction Set
Support
Instructions Detected
SSE2 (SSE2)
Used by default on supported hardware.
 
UNPCKLPD CVTPD2PS CVTSI2SD DIVSD CVTTSD2SI XORPD UCOMISD MOVAPD MULSD ADDSD CMPNLESD ANDPD ANDNPD ORPD SUBSD CMPLTSD CVTPS2PD SQRTSD CMPNLTSD CMPLESD MAXSD MOVDQU
SSSE3 (SSSE3)
Used by default on supported hardware.
 
PSHUFB PALIGNR
SSE 4.2 (SSE4_2)
Used by default on supported hardware.
Found on Intel processors since at least 2010.
Found on AMD processors since Bulldozer (2011).
 
POPCNT
Advanced Vector Extensions (AVX)
Used by default on supported hardware.
Found on Intel processors since Sandy Bridge (2011).
Found on AMD processors since Bulldozer (2011).
 
VZEROUPPER VEXTRACTF128 VINSERTF128 VBROADCASTF128 VBROADCASTSD VBROADCASTSS VPERM2F128 VPERMILPD VPERMILPS VZEROALL
Advanced Vector Extensions 2 (AVX2)
Used by default on supported hardware.
Found on Intel processors since Haswell (2013).
Found on AMD processors since Excavator (2016).
 
VPERM2I128 VEXTRACTI128 VPERMD VPBROADCASTQ VPERMQ VPBLENDD VPBROADCASTD
Advanced Encryption Standard (AES)
Used by default on supported hardware.
Found on Intel processors since Westmere (2011).
Found on AMD processors since Bulldozer (2011).
 
AESENC AESENCLAST AESDEC AESDECLAST AESIMC AESKEYGENASSIST
Vector AES (VAES)
Used by default on supported hardware.
Found on Intel processors since Ice Lake (2019).
Found on AMD processors since Zen 3 (2020).
 
VAESENC VAESENCLAST
Last automated analysis: 30 January 2021

This test profile binary relies on the shared libraries libdeepspeech.so, libdl.so.2, libm.so.6, libgomp.so.1, libpthread.so.0, libc.so.6, librt.so.1.

Recent Test Results

OpenBenchmarking.org Results Compare

1 System - 115 Benchmark Results

Intel Xeon E3-1225 v6 - (2.002 BIOS) - Intel Xeon E3-1200 v6

Ubuntu 20.04 - 5.4.0-70-generic - 1.2.145

1 System - 115 Benchmark Results

Intel Xeon E3-1225 v5 - INTEL H110 - Intel Xeon E3-1200 v5

Ubuntu 20.04 - 5.4.0-66-generic - 1.2.145

1 System - 108 Benchmark Results

2 x Intel Xeon Gold 5218R - Supermicro X11DPX-T - Intel Device 2020

Ubuntu 16.04 - 4.15.0-140-generic - Unity 7.4.0

1 System - 212 Benchmark Results

Intel Core i5-8250U - LENOVO 20L7CTO1WW - Intel Xeon E3-1200 v6

Debian testing - 5.10.0-5-amd64 - GNOME Shell 3.38.4

1 System - 2 Benchmark Results

AMD Ryzen 7 5800X 8-Core - Gigabyte B450 AORUS M - AMD Starship

Ubuntu 20.04 - 5.10.26-051026-generic - nouveau

1 System - 1 Benchmark Result

AMD Ryzen 7 5800X 8-Core - Gigabyte B450 AORUS M - AMD Starship

Ubuntu 20.04 - 5.10.26-051026-generic - nouveau

1 System - 1 Benchmark Result

AMD Ryzen 7 5800X 8-Core - Gigabyte B450 AORUS M - AMD Starship

Ubuntu 20.04 - 5.10.26-051026-generic - nouveau

9 Systems - 442 Benchmark Results

AMD Ryzen 9 5900X 12-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship

Ubuntu 21.04 - 5.12.0-051200rc3daily20210315-generic - GNOME Shell 3.38.3

1 System - 92 Benchmark Results

AMD Ryzen 5 5600X 6-Core - ASRock X570 Phantom Gaming-ITX/TB3 - AMD Device 1480

Ubuntu 18.04 - 5.4.0-70-generic - GNOME Shell 3.28.4

1 System - 323 Benchmark Results

Intel Core i9-11900K - ASUS ROG MAXIMUS XIII HERO - Intel Tiger Lake-H

Ubuntu 21.04 - 5.12.0-051200rc3daily20210315-generic - GNOME Shell 3.38.3

4 Systems - 179 Benchmark Results

Intel Core i5-11600K - ASUS ROG MAXIMUS XIII HERO - Intel Device 43ef

Ubuntu 20.04 - 5.10.13-051013-lowlatency - GNOME Shell 3.36.4

8 Systems - 439 Benchmark Results

AMD Ryzen 7 5800X 8-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship

Ubuntu 21.04 - 5.12.0-051200rc3daily20210315-generic - GNOME Shell 3.38.3

Most Popular Test Results

OpenBenchmarking.org Results Compare

3 Systems - 268 Benchmark Results

Intel Core i5-2520M - HP 161C - Intel 2nd Generation Core DRAM

Ubuntu 18.04 - 4.18.0-20-generic - GNOME Shell 3.28.3

16 Systems - 119 Benchmark Results

Intel Xeon Gold 5218 - GIGABYTE MD61-SC2-00 v01000100 - Intel Sky Lake-E DMI3 Registers

Ubuntu 20.04 - 5.4.0-18-generic - GNOME Shell 3.36.0

2 Systems - 535 Benchmark Results

AMD Ryzen 5 4500U - LENOVO LNVNB161216 - AMD Renoir Root Complex

Ubuntu 20.04 - 5.9.0-050900rc7daily20201002-generic - GNOME Shell 3.36.4

12 Systems - 593 Benchmark Results

AMD Ryzen 5 3600XT 6-Core - MSI X470 GAMING M7 AC - AMD Starship

Ubuntu 20.04 - 5.8.0-050800daily20200622-generic - GNOME Shell 3.36.2

11 Systems - 217 Benchmark Results

AMD Ryzen 5 3600X 6-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship

Ubuntu 20.04 - 5.9.0-050900-generic - GNOME Shell 3.36.4

4 Systems - 55 Benchmark Results

AMD Ryzen 3 3200U - MOTILE PF4PU1F - AMD Raven

Clear Linux OS 32230 - 5.4.16-900.native - GNOME Shell 3.34.3

2 Systems - 151 Benchmark Results

Intel Core i7-10700T - Logic Supply RXM-181 - Intel Comet Lake PCH

Ubuntu 20.10 - 5.8.0-41-generic - GNOME Shell 3.38.2

3 Systems - 174 Benchmark Results

Intel Core i9-10900K - Gigabyte Z490 AORUS MASTER - Intel Comet Lake PCH

Fedora 33 - 5.8.11-300.fc33.x86_64 - GNOME Shell 3.38.0

2 Systems - 403 Benchmark Results

Intel Core i9-10900K - Gigabyte Z490 AORUS MASTER - Intel Comet Lake PCH

Ubuntu 20.04 - 5.4.0-48-generic - GNOME Shell 3.36.4

12 Systems - 229 Benchmark Results

Intel Core i5-10600K - Gigabyte Z490 AORUS MASTER - Intel Comet Lake PCH

Ubuntu 20.04 - 5.9.0-050900-generic - GNOME Shell 3.36.4

3 Systems - 406 Benchmark Results

AMD Ryzen 9 3900XT 12-Core - MSI MEG X570 GODLIKE - AMD Starship

Ubuntu 20.10 - 5.8.0-20-generic - GNOME Shell 3.38.0
Find More Test Results