1

app.py

@@ -54,7 +54,8 @@ def merge_audio_video(entities_num, resize_img_list, text_input):
     
     #Convert text to speech using facebook's latest model from HF hub   
     speech = text2speech(text_input)
-    print(type(speech))
+    print('type of speech : ',type(speech))
+    print(speech)
     wav_audio = AudioSegment.from_file(speech, "flac")  #("/content/gdrive/My Drive/AI/audio1.flac", "flac")
     #convert flac to mp3 audio format 
     print('flac audio read', type(wav_audio))
@@ -95,7 +96,10 @@ fastspeech = gr.Interface.load("huggingface/facebook/fastspeech2-en-ljspeech")
 
 def text2speech(text):
     print('inside testtospeech')
-    return fastspeech(text)
+    speech = fastspeech(text)
+    print(type(speech))
+    print(speech)
+    return speech
     
 def engine(text_input):
     print(" ** Inside Enngine **")