Decode speech¶

This example plots free recall accuracy for a single subject.

[1]:

# Code source: Contextual Dynamics Laboratory
# License: MIT

#import
import quail

# decode speech
recall_data = quail.decode_speech('../data/sample.wav', save=True,
                                  speech_context=['DONKEY', 'PETUNIA'],
                                  keypath='path/to/key.json')

# print results
print(recall_data)

Loading Whisper model: base...

100%|████████████████████████████████████████| 139M/139M [00:01<00:00, 131MiB/s]

Model loaded.
Decoding file 1 of 1: ../data/sample.wav
Error decoding ../data/sample.wav: [Errno 2] No such file or directory: 'ffmpeg'
Error

/home/docs/checkouts/readthedocs.org/user_builds/cdl-quail/envs/latest/lib/python3.11/site-packages/whisper/transcribe.py:132: UserWarning: FP16 is not supported on CPU; using FP32 instead
  warnings.warn("FP16 is not supported on CPU; using FP32 instead")