Closed nchengusaf closed 4 years ago
Hi. I have been having troubles with the prediction; it hasn't been predicting the correct speaker. Here's my layout
/training ---/person ------/84 ----------84_1.wav (7 minutes 46 seconds) ------/174 ----------1741.wav (7 minutes 58 seconds) ------/251 ----------251.wav (7 minutes 04 seconds)
/predict ---84_predict.wav (10 seconds) ---174_predict.wav (10 seconds)
enroll cmd: python speaker-recognition.py -t enroll -i "training" -m model.out
predict cmd: python speaker-recognition.py -t predict -i "predict" -m model.out
results: 84_predict.wav -> 174 174_predict.wav ->174 Is there a reason why I keep seeing the results not predicting correct?
Hi. I have been having troubles with the prediction; it hasn't been predicting the correct speaker. Here's my layout
/training ---/person ------/84 ----------84_1.wav (7 minutes 46 seconds) ------/174 ----------1741.wav (7 minutes 58 seconds) ------/251 ----------251.wav (7 minutes 04 seconds)
/predict ---84_predict.wav (10 seconds) ---174_predict.wav (10 seconds)
enroll cmd: python speaker-recognition.py -t enroll -i "training" -m model.out
predict cmd: python speaker-recognition.py -t predict -i "predict" -m model.out
results: 84_predict.wav -> 174 174_predict.wav ->174 Is there a reason why I keep seeing the results not predicting correct?