esp-sr/docs/zh_CN/benchmark/README.rst
2024-02-22 17:35:39 +08:00

241 lines
10 KiB
ReStructuredText
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

性能测试结果
==============
:link_to_translation:`en:[English]`
AFE
---
资源消耗
~~~~~~~~
.. only:: esp32
+-----------------+-----------------+-----------------+-----------------+
| Algorithm Type | RAM | Average cpu | Frame Length |
| | | loading(compute | |
| | | with 2 cores) | |
+=================+=================+=================+=================+
| AEC(HIGH_PERF) | 114 KB | 11% | 32 ms |
+-----------------+-----------------+-----------------+-----------------+
| NS | 27 KB | 5% | 10 ms |
+-----------------+-----------------+-----------------+-----------------+
| AFE Layer | 73 KB | | |
+-----------------+-----------------+-----------------+-----------------+
.. only:: esp32s3
+-----------------+-----------------+-----------------+-----------------+
| Algorithm Type | RAM | Average cpu | Frame Length |
| | | loading(compute | |
| | | with 2 cores) | |
+=================+=================+=================+=================+
| AEC(LOW_COST) | 152.3 KB | 8% | 32 ms |
+-----------------+-----------------+-----------------+-----------------+
| AEC(HIGH_PERF) | 166 KB | 11% | 32 ms |
+-----------------+-----------------+-----------------+-----------------+
| BSS(LOW_COST) | 198.7 KB | 6% | 64 ms |
+-----------------+-----------------+-----------------+-----------------+
| BSS(HIGH_PERF) | 215.5 KB | 7% | 64 ms |
+-----------------+-----------------+-----------------+-----------------+
| NS(NS_MODE_SSP) | 27 KB | 5% | 10 ms |
+-----------------+-----------------+-----------------+-----------------+
| NS(nsnet1) | 885 KB | 25% | 16 ms |
+-----------------+-----------------+-----------------+-----------------+
| NS(nsnet2) | 375 KB | 12% | 32 ms |
+-----------------+-----------------+-----------------+-----------------+
| MISO | 56 KB | 8% | 16 ms |
+-----------------+-----------------+-----------------+-----------------+
| AFE Layer | 227 KB | | |
+-----------------+-----------------+-----------------+-----------------+
WakeNet
-------
.. _resource-occupancyesp32-1:
资源消耗
~~~~~~~~
.. only:: esp32
+-------------+-------------+-------------+-------------+-------------+
| Model Type | Parameter | RAM | Average | Frame |
| | Num | | Running | Length |
| | | | Time per | |
| | | | Frame | |
+=============+=============+=============+=============+=============+
| Quantised | 41 K | 15 KB | 5.5 ms | 30 ms |
| WakeNet5 | | | | |
+-------------+-------------+-------------+-------------+-------------+
| Quantised | 165 K | 20 KB | 10.5 ms | 30 ms |
| WakeNet5X2 | | | | |
+-------------+-------------+-------------+-------------+-------------+
| Quantised | 371 K | 24 KB | 18 ms | 30 ms |
| WakeNet5X3 | | | | |
+-------------+-------------+-------------+-------------+-------------+
.. _resource-occupancyesp32s3-1:
.. only:: esp32s3
+----------------+-------+---------+----------------+--------------+
| Model Type | RAM | PSRAM | Average | Frame Length |
| | | | Running Time | |
| | | | per Frame | |
+================+=======+=========+================+==============+
| Quantised | 50 KB | 1640 KB | 10.0 ms | 32 ms |
| WakeNet8 @ 2 | | | | |
| channel | | | | |
+----------------+-------+---------+----------------+--------------+
| Quantised | 16 KB | 324 KB | 3.0 ms | 32 ms |
| WakeNet9 @ 2 | | | | |
| channel | | | | |
+----------------+-------+---------+----------------+--------------+
| Quantised | 20 KB | 347 KB | 4.3 ms | 32 ms |
| WakeNet9 @ 3 | | | | |
| channel | | | | |
+----------------+-------+---------+----------------+--------------+
性能测试
~~~~~~~~
+-------------+-------------+-------------+-------------+-------------+
| Distance | Quiet | Stationary | Speech | AEC |
| | | Noise (SNR | Noise (SNR | I |
| | | = 4 dB) | = 4 dB) | nterruption |
| | | | | (-10 dB) |
+=============+=============+=============+=============+=============+
| 1 m | 98% | 96% | 94% | 96% |
+-------------+-------------+-------------+-------------+-------------+
| 3 m | 98% | 96% | 94% | 94% |
+-------------+-------------+-------------+-------------+-------------+
误触发率12 小时 1 次
.. note::
我们在测试中使用了 ESP32-S3-Korvo V4.0 开发板和 WakeNet9(Alexa) 模型。
MultiNet
--------
.. _resource-occupancyesp32-2:
资源消耗
~~~~~~~~
.. only:: esp32
+-------------+-------------+-------------+-------------+-------------+
| Model Type | Internal | PSRAM | Average | Frame |
| | RAM | | Running | Length |
| | | | Time per | |
| | | | Frame | |
+=============+=============+=============+=============+=============+
| MultiNet 2 | 13.3 KB | 9KB | 38 ms | 30 ms |
+-------------+-------------+-------------+-------------+-------------+
.. _resource-occupancyesp32s3-2:
.. only:: esp32s3
+-------------+-------------+-------------+-------------+-------------+
| Model Type | Internal | PSRAM | Average | Frame |
| | RAM | | Running | Length |
| | | | Time per | |
| | | | Frame | |
+=============+=============+=============+=============+=============+
| MultiNet 4 | 16.8KB | 1866 KB | 18 ms | 32 ms |
+-------------+-------------+-------------+-------------+-------------+
| MultiNet 4 | 10.5 KB | 1009 KB | 11 ms | 32 ms |
| Q8 | | | | |
+-------------+-------------+-------------+-------------+-------------+
| MultiNet 5 | 16 KB | 2310 KB | 12 ms | 32 ms |
| Q8 | | | | |
+-------------+-------------+-------------+-------------+-------------+
| MultiNet 6 | 32 KB | 4100 KB | 12 ms | 32 ms |
+-------------+-------------+-------------+-------------+-------------+
Word Error Rate 性能测试
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+-----------+-----------+
| Model | aishell |
| Type | test |
+===========+===========+
| MultiNet | 9.5% |
| 5_cn | |
+-----------+-----------+
| MultiNet | 5.2% |
| 6_cn | |
+-----------+-----------+
.. note::
中文使用没有声调的拼音单元去计算WER。
Speech Commands 性能测试(空调控制场景)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+-----------+-----------+----------+------------+-------------+
| Model | Distance | Quiet | Stationary | Speech |
| Type | | | Noise | Noise |
| | | | (SNR=5~10dB| (SNR=5~10dB |
| | | | dB) | dB) |
+===========+===========+==========+============+=============+
| MultiNet | 3 m | 88.9% | 66.1% | 67.5% |
| 5_cn | | | | |
+-----------+-----------+----------+------------+-------------+
| MultiNet | 3 m | 98.8% | 88.3% | 88.0% |
| 6_cn | | | | |
+-----------+-----------+----------+------------+-------------+
| MultiNet | 3 m | 97.1% | 95.1% | 96.8% |
| 6_cn_ac | | | | |
+-----------+-----------+----------+------------+-------------+
.. note::
MultiNet6_cn_ac在空调场景数据集上进行了进一步的微调所以在空调控制场景具有更好的性能。
TTS
---
资源消耗
~~~~~~~~
Flash image size: 2.2 MB
RAM runtime: 20 KB
性能测试
~~~~~~~~
CPU 负载测试ESP32 @240 MHz
+------------------------------+------+------+------+------+------+------+
| Speech Rate | 0 | 1 | 2 | 3 | 4 | 5 |
+==============================+======+======+======+======+======+======+
| Times faster than real time | 4.5 | 3.2 | 2.9 | 2.5 | 2.2 | 1.8 |
+------------------------------+------+------+------+------+------+------+
NSNET
-----
性能测试
~~~~~~~~
数据集array_onemic_nnoise_20230608(按照亚马逊声学认证标准录制测试集)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+------------------+--------+
| | dnsmos |
+==================+========+
| nsnet1 | 2.4 |
+------------------+--------+
| nsnet2 | 2.71 |
+------------------+--------+