diff options
author | Isabella Gottardi <isabella.gottardi@arm.com> | 2022-02-25 10:56:57 +0000 |
---|---|---|
committer | Isabella Gottardi <isabella.gottardi@arm.com> | 2022-02-25 16:27:50 +0000 |
commit | 177c69d40dddd4db9da7875b9979b82c67609cd1 (patch) | |
tree | ed017bfed0896ac894dd1d776d8ffe6e7236cbb4 /docs/use_cases/kws_asr.md | |
parent | fb93fa74b821d883e7d19999dfd1a358aacebb88 (diff) | |
download | ml-embedded-evaluation-kit-177c69d40dddd4db9da7875b9979b82c67609cd1.tar.gz |
Documentation fixes
Change-Id: I2036332cffee94f1a3b69b391586d0a2f6c9db55
Diffstat (limited to 'docs/use_cases/kws_asr.md')
-rw-r--r-- | docs/use_cases/kws_asr.md | 5 |
1 files changed, 1 insertions, 4 deletions
diff --git a/docs/use_cases/kws_asr.md b/docs/use_cases/kws_asr.md index 22f1e9d..8013634 100644 --- a/docs/use_cases/kws_asr.md +++ b/docs/use_cases/kws_asr.md @@ -241,7 +241,6 @@ For further information, please refer to: - [Configuring with custom TPIP dependencies](../sections/building.md#configuring-with-custom-tpip-dependencies) - [Using Arm Compiler](../sections/building.md#using-arm-compiler) - [Configuring the build for simple-platform](../sections/building.md#configuring-the-build-for-simple_platform) -- [Working with model debugger from Arm Fast Model Tools](../sections/building.md#working-with-model-debugger-from-arm-fast-model-tools) - [Building for different Ethos-U NPU variants](../sections/building.md#building-for-different-ethos_u-npu-variants) > **Note:** If re-building with changed parameters values, we recommend that you clean the build directory and re-run @@ -478,7 +477,7 @@ What the preceding choices do: INFO - Activation buffer (a.k.a tensor arena) size used: 127068 INFO - Number of operators: 1 INFO - Operator 0: ethos-u - + INFO - Model INPUT tensors: INFO - tensor type is INT8 INFO - tensor occupies 11544 bytes with dimensions @@ -574,5 +573,3 @@ The profiling section of the log shows that for the ASR inference: - For FPGA platforms, a CPU cycle count can also be enabled. However, do not use cycle counters for FVP, as the CPU model is not cycle-approximate or cycle-accurate. - - |