Detection of vocal onset using Google transcriber - last release

OS: MacOS Monterey
PsychoPy version: 2024.1.1
Standard Standalone? (y/n) yes
What are you trying to achieve?: I am trying to use Google as a transcriber for my vocal responses but it does not work (telling me that google transcriber is not available offline)

What did you try to make it work?: I followed step-by-step the video tutorial on Youtube about how making Google transcriber to work (i.e., creating an account on Google Cloud, creating a project, activating the speech-to-text API, creating a key, putting the key into Psychopy)

What specifically went wrong when you tried that?:

The experiment starts but it immediately stops and the following error is raised. Everything works fine if I use Whisper instead. However, the problem with Whisper is that it does not seem precise at all for the detection of speech onset: my fast responses are almost all coded as speech onset = 0, and it’s clearly not the case.

I’d really appreciate if you could help (either to make google transcriber work offline or by making the Whisper onset detection reasonable). Thanks in advance to all contributors for your amazing work with this amazing program :slight_smile:

File “/Applications/PsychoPy.app/Contents/Resources/lib/python3.8/psychopy/sound/transcribe.py”, line 754, in getTranscriberInterface
transcriber = transcribers[engine]
KeyError: ‘google’

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File “/Users/lorenzociccione/Desktop/priming/UNMASKED/FRAMES/priming_naming_frames/priming_naming_lastrun.py”, line 1410, in
run(
File “/Users/lorenzociccione/Desktop/priming/UNMASKED/FRAMES/priming_naming_frames/priming_naming_lastrun.py”, line 394, in run
setupTranscriber(
File “/Applications/PsychoPy.app/Contents/Resources/lib/python3.8/psychopy/sound/transcribe.py”, line 798, in setupTranscriber
transcriber = getTranscriberInterface(engine)
File “/Applications/PsychoPy.app/Contents/Resources/lib/python3.8/psychopy/sound/transcribe.py”, line 756, in getTranscriberInterface
raise ValueError(
ValueError: Transcriber with engine name google not found.
################# Experiment ended with exit code 1 [pid:1249] #################