mirror of
https://github.com/home-assistant/home-assistant.io.git
synced 2025-05-07 03:28:58 +00:00
4c95772e2e
* Assist: local pipeline: add step to install openWakeWord - closes #30364 * Fix markdown
78 lines
4.9 KiB
Markdown
78 lines
4.9 KiB
Markdown
---
|
|
title: "Installing a local Assist pipeline"
|
|
---
|
|
|
|
In Home Assistant, the Assist pipelines are made up of various components that together form a voice assistant.
|
|
|
|
For each component you can choose from different options. There is a speech-to-text and text-to-speech option that runs entirely local.
|
|
|
|
The speech-to-text option is [Whisper](https://github.com/openai/whisper). It's an open source AI model that supports [various languages](https://github.com/openai/whisper#available-models-and-languages). We use a forked version called [faster-whisper](https://github.com/guillaumekln/faster-whisper). On a Raspberry Pi 4, it takes around 8 seconds to process incoming voice commands. On an Intel NUC it is done in under a second.
|
|
|
|
For text-to-speech we have developed [Piper](https://github.com/rhasspy/piper). Piper is a fast, local neural text-to-speech system that sounds great and is optimized for the Raspberry Pi 4. It supports [many languages](https://rhasspy.github.io/piper-samples/). On a Raspberry Pi, using medium quality models, it can generate 1.6s of voice in a second.
|
|
|
|
## Prerequisites
|
|
|
|
- Home Assistant Operating System
|
|
|
|
## Installing a local Assist pipeline
|
|
|
|
For the quickest way to get your local Assist pipeline started, follow these steps:
|
|
|
|
1. Install the add-ons to convert text into speech and vice versa.
|
|
- Install the {% my supervisor_addon addon="core_whisper" title="**Whisper**" %} and the {% my supervisor_addon addon="core_piper" title="**Piper**" %} add-ons.
|
|
|
|
- If you want to use a wake word, also install the {% my supervisor_addon addon="core_openwakeword" title="**openWakeWord**" %} add-on.
|
|
- Start the add-ons.
|
|
- Once the add-ons are started, head over to the integrations under {% my integrations title="**Settings** > **Devices & Services**" %}.
|
|
- You should now see Piper and Whisper being discovered by the [Wyoming integration](/integrations/wyoming/).
|
|
|
|
- For each integration, select **Configure**.
|
|
- Once the setup is complete, you should see both Piper and Whisper (and, optionally, also openWakeword) in one integration.
|
|
|
|
|
|
- **Whisper** converts speech into text.
|
|
- **Piper** converts text into speech.
|
|
- **Wyoming** is the protocol they are both using to communicate.
|
|
2. Setup your assistant.
|
|
|
|
- Go to {% my voice_assistants title="**Settings** > **Voice assistants**" %} and select **Add assistant**.
|
|
|
|
|
|
- **Troubleshooting**: If you do not see any assistants here, you are not using the default configuration. In this case, you need to add the following to your `configuration.yaml` file:
|
|
|
|
```yaml
|
|
# Example configuration.yaml entry
|
|
assist_pipeline:
|
|
```
|
|
|
|
- Enter a name. You can pick any name that is meaningful to you.
|
|
- Select the language that you want to speak.
|
|
- Under **Conversation agent**, select **Home Assistant**.
|
|
- Under **Speech-to-text**, select **faster-whisper**.
|
|
- Under **Text-to-speech**, select **piper**.
|
|
- Depending on your language, you may be able to select different language variants.
|
|
- If you like, pick one of the predefined wake words.
|
|
|
|
- You can even [define your own a wake word](/voice_control/create_wake_word/). This is not difficult to do, but you will need to set aside a bit of time for this.
|
|
- Once you defined your own wake word, it will show in this pick list.
|
|
|
|
3. That's it. You ensured your voice commands can be processed locally on your device.
|
|
4. If you haven't done so yet, [expose your devices to Assist](/voice_control/voice_remote_expose_devices/#exposing-your-devices).
|
|
- Otherwise you won't be able to control them by voice.
|
|
|
|
## Fine-tuning Whisper and Piper for your setup
|
|
|
|
You would like to tweak the configuration for better performance or accuracy?
|
|
View some of the options in the video below. Explained by Mike Hansen, creator of Rhasspy, Piper, and Wyoming.
|
|
|
|
<lite-youtube videoid="Tk-pnm7FY7c" videoStartAt="1589" videotitle="Configure your local Assist pipeline for your setup"></lite-youtube>
|
|
|
|
The options are also documented in the add-on itself. Go to the {% my supervisor_addon addon="core_whisper" title="**Whisper**" %} or the {% my supervisor_addon addon="core_piper" title="**Piper**" %} add-on and open the **Documentation** page.
|
|
|
|
## Related topics
|
|
|
|
- [Create your own wake word](/voice_control/create_wake_word/)
|
|
- [Expose your devices to Assist](/voice_control/voice_remote_expose_devices/#exposing-your-devices)
|
|
- [Whisper for speech-to-text](https://github.com/openai/whisper)
|
|
- [Piper for text-to-speech](https://github.com/rhasspy/piper)
|