esp-sr/docs/zh_CN/benchmark/README.rst
2023-03-16 17:00:12 +08:00

211 lines
9.4 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.

资源消耗
========
:link_to_translation:`en:[English]`
AFE
---
资源占用
~~~~~~~~
.. 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 | 27 KB | 5% | 10 ms |
+-----------------+-----------------+-----------------+-----------------+
| MISO | 56 KB | 8% | 16 ms |
+-----------------+-----------------+-----------------+-----------------+
| AFE Layer | 227 KB | | |
+-----------------+-----------------+-----------------+-----------------+
WakeNet
-------
.. _resource-occupancyesp32-1:
资源占用
~~~~~~~~
.. 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:
资源占用
~~~~~~~~
.. 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 | 48 KB | 4000 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
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+-----------+-----------+----------+------------+-------------+
| Model | Distance | Quiet | Stationary | Speech |
| Type | | | Noise | Noise |
| | | | (SNR=5~10dB| (SNR=5~10dB |
| | | | dB) | dB) |
+===========+===========+==========+============+=============+
| MultiNet | 3 m | | | |
| 5_cn | | | | |
+-----------+-----------+----------+------------+-------------+
| MultiNet | 3 m | | | |
| 6_cn | | | | |
+-----------+-----------+----------+------------+-------------+
TTS
---
资源占用
~~~~~~~~
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 |
+------------------------------+------+------+------+------+------+------+