@ -145,15 +145,15 @@ Once you have created the edge device registration in your IoT Hub, you can set
**The IoT Edge runtime only runs Linux containers.** It can be run on Linux, or on Windows using Linux Virtual Machines.
* If you are using a Raspberry Pi as your IoT device, then this runs a supported version of Linux and can host the IoT Edge runtime. Follow the [Install Azure IoT Edge for Linux guide on Microsoft docs](https://docs.microsoft.com/azure/iot-edge/how-to-install-iot-edge?WT.mc_id=academic-17441-jabenn) to install IoT Edge and set the connection string.
* If you are using a Raspberry Pi as your IoT device, then this runs a supported version of Linux and can host the IoT Edge runtime. Follow the [install Azure IoT Edge for Linux guide on Microsoft docs](https://docs.microsoft.com/azure/iot-edge/how-to-install-iot-edge?WT.mc_id=academic-17441-jabenn) to install IoT Edge and set the connection string.
> 💁 Remember, Raspberry Pi OS is a variant of Debian Linux.
* If you are not using a Raspberry Pi, but have a Linux computer, you can run the IoT Edge runtime. Follow the [Install Azure IoT Edge for Linux guide on Microsoft docs](https://docs.microsoft.com/azure/iot-edge/how-to-install-iot-edge?WT.mc_id=academic-17441-jabenn) to install IoT Edge and set the connection string.
* If you are not using a Raspberry Pi, but have a Linux computer, you can run the IoT Edge runtime. Follow the [install Azure IoT Edge for Linux guide on Microsoft docs](https://docs.microsoft.com/azure/iot-edge/how-to-install-iot-edge?WT.mc_id=academic-17441-jabenn) to install IoT Edge and set the connection string.
* If you are using Windows, you can install the IoT Edge runtime in a Linux Virtual Machine by following the [Install and start the IoT Edge runtime section of the Deploy your first IoT Edge module to a Windows device quickstart on Microsoft docs](https://docs.microsoft.com/azure/iot-edge/quickstart?WT.mc_id=academic-17441-jabenn#install-and-start-the-iot-edge-runtime). You can stop when you reach the *Deploy a module* section.
* If you are using Windows, you can install the IoT Edge runtime in a Linux Virtual Machine by following the [install and start the IoT Edge runtime section of the deploy your first IoT Edge module to a Windows device quickstart on Microsoft docs](https://docs.microsoft.com/azure/iot-edge/quickstart?WT.mc_id=academic-17441-jabenn#install-and-start-the-iot-edge-runtime). You can stop when you reach the *Deploy a module* section.
* If you are using macOS, you can create a virtual machine (VM) in the cloud to use for your IoT Edge device. These are computers you can create in the cloud and access over the internet. You can create a Linux VM that has IoT Edge installed. Follow the [Create a virtual machine running IoT Edge guide](vm-iotedge.md) for instructions on how to do this.
* If you are using macOS, you can create a virtual machine (VM) in the cloud to use for your IoT Edge device. These are computers you can create in the cloud and access over the internet. You can create a Linux VM that has IoT Edge installed. Follow the [create a virtual machine running IoT Edge guide](vm-iotedge.md) for instructions on how to do this.
## Export your model
@ -463,7 +463,7 @@ Your container can now be deployed to your IoT Edge device. To deploy you need t
1. Connect to the IoT edge device:
* If you are using a Raspberry Pi to run IoT Edge, connect using ssh either from your terminal, or via a remote SSH session in VS Code
* If you are running IoT Edge in a Linux container on Windows, follow the steps in the [Verify successful configuration guide](https://docs.microsoft.com/azure/iot-edge/how-to-install-iot-edge-on-windows?view=iotedge-2018-06&tabs=powershell&WT.mc_id=academic-17441-jabenn#verify-successful-configuration) to connect to the IoT Edge device.
* If you are running IoT Edge in a Linux container on Windows, follow the steps in the [verify successful configuration guide](https://docs.microsoft.com/azure/iot-edge/how-to-install-iot-edge-on-windows?view=iotedge-2018-06&tabs=powershell&WT.mc_id=academic-17441-jabenn#verify-successful-configuration) to connect to the IoT Edge device.
* If you are running IoT Edge on a virtual machine, you can SSH into the machine using the `adminUsername` and `password` you set when creating the VM, and using either the IP address or DNS name:
```sh
@ -527,9 +527,9 @@ Your container can now be deployed to your IoT Edge device. To deploy you need t
* If you are on the same machine that IoT Edge is running, you can use `localhost` as the host name.
* If you are using a VM, you can use either the IP address or the DNS name of the VM
* Otherwise you can obtain the IP address of the machine running IoT Edge:
* On Windows 10, follow the [Find your IP address guide](https://support.microsoft.com/windows/find-your-ip-address-f21a9bbc-c582-55cd-35e0-73431160a1b9?WT.mc_id=academic-17441-jabenn)
* On macOS, follow the [How to find you IP address on a Mac guide](https://www.hellotech.com/guide/for/how-to-find-ip-address-on-mac)
* On linux, follow the section on finding your private IP address in the [How to find your IP address in Linux guide](https://opensource.com/article/18/5/how-find-ip-address-linux)
* On Windows 10, follow the [find your IP address guide](https://support.microsoft.com/windows/find-your-ip-address-f21a9bbc-c582-55cd-35e0-73431160a1b9?WT.mc_id=academic-17441-jabenn)
* On macOS, follow the [how to find you IP address on a Mac guide](https://www.hellotech.com/guide/for/how-to-find-ip-address-on-mac)
* On linux, follow the section on finding your private IP address in the [how to find your IP address in Linux guide](https://opensource.com/article/18/5/how-find-ip-address-linux)
1. You can test the container with a local file by running the following curl command:
@ -603,8 +603,8 @@ Do some timings and compare if the call to your edge device is faster or slower
## Review & Self Study
* Read more about containers on the [OS-level virtualization page on Wikipedia](https://wikipedia.org/wiki/OS-level_virtualization)
* Read more on edge computing, with an emphasis on how 5G can help expand edge computing in the [What is edge computing and why does it matter? article on NetworkWorld](https://www.networkworld.com/article/3224893/what-is-edge-computing-and-how-it-s-changing-the-network.html)
* Learn more about running AI services in IoT Edge by watching the [Learn How to Use Azure IoT Edge on a Pre-Built AI Service on the Edge to do Language Detection episode of Learn Live on Microsoft Channel9](https://channel9.msdn.com/Shows/Learn-Live/Sharpen-Your-AI-Edge-Skills-Episode-4-Learn-How-to-Use-Azure-IoT-Edge-on-a-Pre-Built-AI-Service-on-t?WT.mc_id=academic-17441-jabenn)
* Read more on edge computing, with an emphasis on how 5G can help expand edge computing in the [what is edge computing and why does it matter? article on NetworkWorld](https://www.networkworld.com/article/3224893/what-is-edge-computing-and-how-it-s-changing-the-network.html)
* Learn more about running AI services in IoT Edge by watching the [learn how to use Azure IoT Edge on a pre-built AI service on the Edge to do language detection episode of Learn Live on Microsoft Channel9](https://channel9.msdn.com/Shows/Learn-Live/Sharpen-Your-AI-Edge-Skills-Episode-4-Learn-How-to-Use-Azure-IoT-Edge-on-a-Pre-Built-AI-Service-on-t?WT.mc_id=academic-17441-jabenn)
@ -157,7 +157,7 @@ Wake word detection usually uses a technique know an TinyML, that is converting
To avoid the complexity of training and using a wake word model, the smart timer you are building in this lesson will use a button to turn on the speech recognition.
> 💁 If you want to try creating a wake word detection model to run on the Wio Terminal or Raspberry Pi, check out this [Responding to your voice tutorial by Edge Impulse](https://docs.edgeimpulse.com/docs/responding-to-your-voice). If you want to use your computer to do this, you can try the [Get started with Custom Keyword quickstart on the Microsoft docs](https://docs.microsoft.com/azure/cognitive-services/speech-service/keyword-recognition-overview?WT.mc_id=academic-17441-jabenn).
> 💁 If you want to try creating a wake word detection model to run on the Wio Terminal or Raspberry Pi, check out this [responding to your voice tutorial by Edge Impulse](https://docs.edgeimpulse.com/docs/responding-to-your-voice). If you want to use your computer to do this, you can try the [get started with Custom Keyword quickstart on the Microsoft docs](https://docs.microsoft.com/azure/cognitive-services/speech-service/keyword-recognition-overview?WT.mc_id=academic-17441-jabenn).
## Convert speech to text
@ -214,9 +214,9 @@ What do you think the future holds for speech recognition?
## Review & Self Study
* Read about the different microphone types and how they work on the [What's the difference between dynamic and condenser microphones article on Musician's HQ](https://musicianshq.com/whats-the-difference-between-dynamic-and-condenser-microphones/).
* Read more on the Cognitive Services speech service on the [Speech service documentation on Microsoft Docs](https://docs.microsoft.com/azure/cognitive-services/speech-service/?WT.mc_id=academic-17441-jabenn)
* Read about keyword spotting on the [Keyword recognition documentation on Microsoft Docs](https://docs.microsoft.com/azure/cognitive-services/speech-service/keyword-recognition-overview?WT.mc_id=academic-17441-jabenn)
* Read about the different microphone types and how they work on the [what's the difference between dynamic and condenser microphones article on Musician's HQ](https://musicianshq.com/whats-the-difference-between-dynamic-and-condenser-microphones/).
* Read more on the Cognitive Services speech service on the [speech service documentation on Microsoft Docs](https://docs.microsoft.com/azure/cognitive-services/speech-service/?WT.mc_id=academic-17441-jabenn)
* Read about keyword spotting on the [keyword recognition documentation on Microsoft Docs](https://docs.microsoft.com/azure/cognitive-services/speech-service/keyword-recognition-overview?WT.mc_id=academic-17441-jabenn)
@ -138,6 +138,6 @@ The microphone and speakers need to be connected, and configured.
You will hear the audio bing played back through the speakers. Adjust the output volume on your speaker as necessary.
1. If you need to adjust the volume of the built-in microphone port, or adjust the gain of the microphone, you can use the `alsamixer` utility. You can read more on this utility on thw [Linux alsamixer man page](https://linux.die.net/man/1/alsamixer)
1. If you need to adjust the volume of the built-in microphone port, or adjust the gain of the microphone, you can use the `alsamixer` utility. You can read more on this utility on the [Linux alsamixer man page](https://linux.die.net/man/1/alsamixer)
1. If you get errors playing back the audio, check the card you set as the `defaults.pcm.card` in the `alsa.conf` file.
@ -98,7 +98,7 @@ Once each buffer has been captured, it can be written to the flash memory. Flash
}
```
This configures the flash memory on teh Wio Terminal to write to, and sets up the buffers based off the grain size of the flash memory. This is in an `init` method, rather than a constructor as this needs to be called after the flash memory has been set up in the `setup` function.
This configures the flash memory on the Wio Terminal to write to, and sets up the buffers based off the grain size of the flash memory. This is in an `init` method, rather than a constructor as this needs to be called after the flash memory has been set up in the `setup` function.
1. Add the following code to the `public` section:
@ -157,7 +157,7 @@ Once each buffer has been captured, it can be written to the flash memory. Flash
| Constant | Value | Description |
| --------------------- | -----: | - |
| RATE | 16000 | The sample rate for the audio. !6,000 is 16KHz |
| RATE | 16000 | The sample rate for the audio. 16,000 is 16KHz |
| SAMPLE_LENGTH_SECONDS | 4 | The length of audio to capture. This is set to 4 seconds. To record longer audio, increase this. |
| SAMPLES | 64000 | The total number of audio samples that will be captured. Set to the sample rate * the number of seconds |
| BUFFER_SIZE | 128044 | The size of the audio buffer to capture. Audio will be captured as a WAV file, which is 44 bytes of header, then 128,000 bytes of audio date (each sample is 2 bytes) |
@ -517,7 +517,7 @@ Once each buffer has been captured, it can be written to the flash memory. Flash
}
```
This code checks hte C button, and if this is pressed and recording hasn't started, then the `_isRecording` field of the `Mic` class is set to true. This will cause the `audioCallback` method of the `Mic` class to store audio until 4 seconds has been captured. Once 4 seconds of audio has been captured, the `_isRecording` field is set to false, and the `_isRecordingReady` field is set to true. This is then checked in the `loop` function, and when true the `processAudio` function is called, then the mic class is reset.
This code checks the C button, and if this is pressed and recording hasn't started, then the `_isRecording` field of the `Mic` class is set to true. This will cause the `audioCallback` method of the `Mic` class to store audio until 4 seconds has been captured. Once 4 seconds of audio has been captured, the `_isRecording` field is set to false, and the `_isRecordingReady` field is set to true. This is then checked in the `loop` function, and when true the `processAudio` function is called, then the mic class is reset.
1. Build this code, upload it to your Wio Terminal and test it out through the serial monitor. Press the C button (the one on the left-hand side, closest to the power switch), and speak. 4 seconds of audio will be captured.
@ -87,7 +87,7 @@ To use LUIS, you need to create an authoring resource.
> 💁 There is a field for a prediction resource. You can create a second resource just for prediction, but the free authoring resource allows 1,000 predictions a month which should be enough for development, so you can leave this blank.
1. Read through the guide that appears once you cerate the app to get an understanding of the steps you need to take to train the language understanding model. Close this guide when you are done.
1. Read through the guide that appears once you create the app to get an understanding of the steps you need to take to train the language understanding model. Close this guide when you are done.
## Intents and entities
@ -102,7 +102,7 @@ Some examples:
| "Cancel my timer" | *cancel a timer* | None |
| "Order 3 large pineapple pizzas and a caesar salad" | *order food* | *3 large pineapple pizzas*, *caesar salad* |
✅ With the sentences you though about earlier, what would be the intent and any entities in that sentence?
✅ With the sentences you thought about earlier, what would be the intent and any entities in that sentence?
To train LUIS, first you set the entities. These can be a fixed list of terms, or learned from the text. For example, you could provide a fixed list of food available from your menu, with variations (or synonyms) of each word, such as *egg plant* and *aubergine* as variations of *aubergine*. LUIS also has pre-built entities that can be used, such as numbers and locations.
@ -262,7 +262,7 @@ For a smart timer, we want a response straight away, so we can tell the user tha
Rather than calling LUIS from the IoT device, you can use serverless code with a different type of trigger - an HTTP trigger. This allows your function app to listen for REST requests, and respond to them. This function will be a REST endpoint your device can call.
> 💁 Although you can call LUIS directly from your IoT device, it's better to use something like serverless code. This way when of you want to change the LUIS app that you call, for example when you train a better model or train a model in a different language, you only have to update your cloud code, not re-deploy code to potentially thousands or millions of IoT device.
> 💁 Although you can call LUIS directly from your IoT device, it's better to use something like serverless code. This way when you want to change the LUIS app that you call, for example when you train a better model or train a model in a different language, you only have to update your cloud code, not re-deploy code to potentially thousands or millions of IoT device.
### Task - create a serverless functions app
@ -500,9 +500,9 @@ Rather than calling LUIS from the IoT device, you can use serverless code with a
Find your IP address:
* On Windows 10, follow the [Find your IP address guide](https://support.microsoft.com/windows/find-your-ip-address-f21a9bbc-c582-55cd-35e0-73431160a1b9?WT.mc_id=academic-17441-jabenn)
* On macOS, follow the [How to find you IP address on a Mac guide](https://www.hellotech.com/guide/for/how-to-find-ip-address-on-mac)
* On linux, follow the section on finding your private IP address in the [How to find your IP address in Linux guide](https://opensource.com/article/18/5/how-find-ip-address-linux)
* On Windows 10, follow the [find your IP address guide](https://support.microsoft.com/windows/find-your-ip-address-f21a9bbc-c582-55cd-35e0-73431160a1b9?WT.mc_id=academic-17441-jabenn)
* On macOS, follow the [how to find you IP address on a Mac guide](https://www.hellotech.com/guide/for/how-to-find-ip-address-on-mac)
* On linux, follow the section on finding your private IP address in the [how to find your IP address in Linux guide](https://opensource.com/article/18/5/how-find-ip-address-linux)
Once you have your IP address, you will able to access the function at `http://<IP_ADDRESS>:7071/api/text-to-timer`, where `<IP_ADDRESS>` will be your IP address, for example `http://192.168.1.10:7071/api/text-to-timer`.
@ -523,7 +523,7 @@ There are many ways to request the same thing, such as setting a timer. Think of
## Review & Self Study
* Read more about LUIS and it's capabilities on the [Language Understanding (LUIS) documentation page on Microsoft docs](https://docs.microsoft.com/azure/cognitive-services/luis/?WT.mc_id=academic-17441-jabenn)
* Read more about language understanding on the [Natural-language understanding page on Wikipedia](https://wikipedia.org/wiki/Natural-language_understanding)
* Read more about language understanding on the [natural-language understanding page on Wikipedia](https://wikipedia.org/wiki/Natural-language_understanding)
* Read more on HTTP triggers in the [Azure Functions HTTP trigger documentation on Microsoft docs](https://docs.microsoft.com/azure/azure-functions/functions-bindings-http-webhook-trigger?tabs=python&WT.mc_id=academic-17441-jabenn)
@ -119,9 +119,9 @@ SSML has ways to change how words are spoken, such as adding emphasis to certain
## Review & Self Study
* Read more on speech synthesis on the [Speech synthesis page on Wikipedia](https://wikipedia.org/wiki/Speech_synthesis)
* Read more on ways criminals are using speech synthesis to steal on the [Fake voices 'help cyber crooks steal cash' story on BBC news](https://www.bbc.com/news/technology-48908736)
* Learn more about the risks to voice actors from synthesized versions of their voices in the [This TikTok Lawsuit Is Highlighting How AI Is Screwing Over Voice Actors article on Vice](https://www.vice.com/en/article/z3xqwj/this-tiktok-lawsuit-is-highlighting-how-ai-is-screwing-over-voice-actors)
* Read more on speech synthesis on the [speech synthesis page on Wikipedia](https://wikipedia.org/wiki/Speech_synthesis)
* Read more on ways criminals are using speech synthesis to steal on the [fake voices 'help cyber crooks steal cash' story on BBC news](https://www.bbc.com/news/technology-48908736)
* Learn more about the risks to voice actors from synthesized versions of their voices in the [this TikTok lawsuit is highlighting how AI is screwing over voice actors article on Vice](https://www.vice.com/en/article/z3xqwj/this-tiktok-lawsuit-is-highlighting-how-ai-is-screwing-over-voice-actors)
@ -165,9 +165,9 @@ How can machine translations benefit other IoT applications beyond smart devices
## Review & Self Study
* Read more on machine translation on the [Machine translation page on Wikipedia](https://wikipedia.org/wiki/Machine_translation)
* Read more on neural machine translation on the [Neural machine translation page on Wikipedia](https://wikipedia.org/wiki/Neural_machine_translation)
* Check out the list of supported languages for the Microsoft speech services in the [Language and voice support for the Speech service documentation on Microsoft Docs](https://docs.microsoft.com/azure/cognitive-services/speech-service/language-support?WT.mc_id=academic-17441-jabenn)
* Read more on machine translation on the [machine translation page on Wikipedia](https://wikipedia.org/wiki/Machine_translation)
* Read more on neural machine translation on the [neural machine translation page on Wikipedia](https://wikipedia.org/wiki/Neural_machine_translation)
* Check out the list of supported languages for the Microsoft speech services in the [language and voice support for the Speech service documentation on Microsoft Docs](https://docs.microsoft.com/azure/cognitive-services/speech-service/language-support?WT.mc_id=academic-17441-jabenn)
@ -84,7 +84,7 @@ The speech service can take speech and not only convert to text in the same lang
## Translate text using the translator service
The speech service doesn't support translation pf text back to speech, instead you can use the Translator service to translate the text. This service has a REST API you can use to translate the text.
The speech service doesn't support translation of text back to speech, instead you can use the Translator service to translate the text. This service has a REST API you can use to translate the text.
### Task - use the translator resource to translate text
Jim Bennett
4 years ago
committed by
GitHub