howl
howl copied to clipboard
Wake word detection modeling toolkit for Firefox Voice, supporting open datasets like Speech Commands and Common Voice.
why max window size == 500ms ? Is it because the duration of a word is about 500ms?
1. Document the codebase. 2. Generate HTML documentation using Sphinx with the Napoleon and autodoc extensions. 3. Write some tutorials and getting started guides. 4. Create a GitHub page for...
Currently, the training process only uses positive dev/test sets for intermediate evaluation. We will first need to update the code to use some of negative sets before we can implement...
https://optuna.org/ might be a good option
Hello, Can I build my own french dataset for some keywords using download_mfa.sh and generate_dataset.sh like "Preparing a Dataset" ? If yes, can you explain me some tips for that?...
some files under howl/data/dataset (labeller, phone) should be located outside as a common module that can be added separately I have noticed some classes are incorrectly located and can be...
Instead of searching for exact match, we can include singular or plural forms Maybe we can use some features of nltk https://www.nltk.org/index.html??
`token type = 'phone'` setting may not be working. we need to check its functionality and make sure an example is included
Hello, I managed to trained the mdoel and I have attached my model in the following link: https://drive.google.com/drive/folders/1UE5NydQhPB8-TeLeLeoc7GOaLTMIBwfP?usp=sharing. But when I run the howl.run.demo, it didn't detect any result. I...
I am currently building a pipeline for a research project which requires KWS - I am confused which one would be better off. In our use-case, we want to identify...