Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -17,14 +17,14 @@ Here are a couple of things I'll be looking next:
- [X] a 'proper' skills framework, using plugin technology
- [X] an event framework to be able to add functionality via plugins

Google have stopped supporting the APi we previously used to convert speech audio to text, so I've not moved to an offline library called Vosk. Its very easy to setup - just type:
Google have stopped supporting the APi we previously used to convert speech audio to text, so I've now moved to an offline library called Vosk. Its very easy to setup - just type:

``` bash
pip install vosk
```

and you'll install the main library for Python.
You'll also need to download a model from <https://alphacephei.com/vosk/models>. I went with the `vosk-model-en-us-0.22` model, which although large is ery accurate. To install the model, just unzip the vosk-model-en-us-0.22.zip file and rename the unzipped folder to `model` and put that in the root of the git repository.
You'll also need to download a model from <https://alphacephei.com/vosk/models>. I went with the `vosk-model-en-us-0.22` model, which although is large but very accurate. To install the model, just unzip the vosk-model-en-us-0.22.zip file and rename the unzipped folder to `model` and put that in the root of the git repository.

## Code Refactor

Expand Down