Update app.py

app.py

@@ -130,41 +130,28 @@ class DataViewerApp:
 
         return self.get_page_data(self.current_page)
     def trim_audio(self, text,data_oudio):
-  # Load audio
-        #row = self.data.iloc[self.current_selected]
-        #row['text'] = text  # Use .loc for safer row modification
-        #self.data.iloc[self.current_selected] = row
         audios_data = []
         audios_samplerate = []
-
         sr,audio=data_oudio
-        #if sr!=16000:
-        namefile=f"{text}.wav"
-        sf.write(namefile, audio, sr,format='WAV')
-        return self.GetDataset_2(namefile)
-            #audio, samplerate = librosa.load("tempppp.wav", sr=16000)
-            #audios_data.append(audio)
-           # secs=round(len(audios_data)/samplerate,2)
-            #audios_samplerate.append(samplerate)
-        #else:
-          #  secs=round(len(audio)/sr,2)
-           # audios_data.append(audio)
-            #audios_samplerate.append(sr)
-        #secs.append(round(len(audios_data)/samplerate,2))
-        #self.df['secs'] = secs
-        #self.df['audio'] = audios_data
-        #self.df['samplerate'] = sr
-        #self.df['text'] =text
-        #self.df =self.df[['text','audio','samplerate','secs']]
-        #self.df.reset_index(drop=True, inplace=True)
-        #self.data =self.df[['text','speaker_id','secs']]
-
-
-        #self.sdata =df['audio'].to_list()
-
-
-
-        #return self.data,5.8
+        audio=audio.astype(np.float32)
+        audio/=np.max(np.abs(audio))
+        audio=librosa.resample(audio,orig_sr=sr,target_sr=16000)
+        audios_data.append(audio)
+        secs=round(len(audios_data)/16000,2)
+        audios_samplerate.append(16000)
+        df = pd.DataFrame()
+        df['secs'] = secs
+        df['audio'] =[ audio]
+        df['samplerate'] = 16000
+        df['text'] =text
+        df['speaker_id'] =self.speaker_id
+        df['_speaker_id'] =self.speaker_id
+        df['flag']=1
+        df = df[['text','audio','samplerate','secs','speaker_id','_speaker_id','flag']]
+        self.df = pd.concat([self.df, df], axis=0, ignore_index=True)
+        self.data =self.df[['text','speaker_id','secs','flag']]
+        self.sdata =self.df['audio'].to_list()
+        return self.get_page_data(self.current_page) 
     def connect_drive(self):
         from google.colab import drive
         drive.mount('/content/drive')