harshit345
/

xlsr-wav2vec-speech-emotion-recognition

Audio Classification

Model card Files Files and versions

marrnavarro commited on Mar 16, 2023

Commit

d94d1d6

·

1 Parent(s): 7fd191e

Update README.md

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -55,8 +55,9 @@ def predict(path, sampling_rate):
 # prediction
 ~~~
 # path for a sample
-path = '/data/jtes_v1.1/wav/f01/ang/f01_ang_01.wav'
-outputs = predict(path, sampling_rate)
 ~~~
 ~~~
 [{'Emotion': 'anger', 'Score': '78.3%'},

 # prediction
 ~~~
 # path for a sample
+path = '/data/jtes_v1.1/wav/f01/ang/f01_ang_01.wav'
+data, sampling_rate =  librosa.load(path)
+outputs = predict(data, sampling_rate)
 ~~~
 ~~~
 [{'Emotion': 'anger', 'Score': '78.3%'},