akadmin/openwakeword
1
0
Fork 0
mirror of https://github.com/dscripka/openWakeWord.git synced 2026-08-27 18:17:20 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

corrected link hey_mycroft.md performance details

Browse source
This commit is contained in:
Aditya Shankar 2025-02-01 13:27:31 +01:00 • committed by GitHub
parent 7607f95985
commit bb9d7e0a08
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
docs/models/hey_mycroft.md
View file

@ -75,8 +75,8 @@ The positive test examples of the "hey mycroft" wakeword were collected manually
The false-accept/false-reject curve for the model on the test data is shown below. Decreasing the `threshold` parameter when using the model will increase the false-accept rate and decrease the false-reject rate.
![FPR/FRR curve for "hey mycroft" pre-trained model](images/hey_mycroft_performance_plot.png)
![FPR/FRR curve for "hey mycroft" pre-trained model](images/hey_mycroft_performance.png)
# Other Considerations
While the model was trained to be robust to background noise and reverberation, it will still perform the best when the audio is relatively clean and free of overly loud background noise. In particular, the presence of audio playback of music/speech from the same device that is capturing the microphone stream may result in significantly higher false-reject rates unless acoustic echo cancellation (AEC) is performed via hardware or software.
While the model was trained to be robust to background noise and reverberation, it will still perform the best when the audio is relatively clean and free of overly loud background noise. In particular, the presence of audio playback of music/speech from the same device that is capturing the microphone stream may result in significantly higher false-reject rates unless acoustic echo cancellation (AEC) is performed via hardware or software.