aa

app.py

@@ -17,6 +17,7 @@ headers = {"Authorization": f"Bearer {HF_TOKEN}"}
 
 # Text-to-Speech
 LANGUAGES = list(CoquiTTS.langs.keys())
+print(f"Languages for Coqui are: {LANGUAGES}")
 coquiTTS = CoquiTTS()
 
 
@@ -42,8 +43,8 @@ def whisper_stt(audio):
 
 # Processing input Audio
 def fun_engine(audio) : 
-  #text1 = whisper_stt(audio)
-  text1 = model.transcribe(audio)["text"]
+  text1 = whisper_stt(audio)
+  #text1 = model.transcribe(audio)["text"]
   text2 = lang_model_response(text1)
   speech = tts(text, 'en')
   return text1, text2, speech
@@ -82,11 +83,9 @@ def tts(text, language):
         coquiTTS.get_tts(text, fp, speaker = {"language" : language})
         return fp.name
 
-#inputs = [gr.Textbox(label="Input", value=CoquiTTS.langs["en"]["sentence"], max_lines=3), 
-#            gr.Radio(label="Language", choices=LANGUAGES, value="en")]
-#outputs = gr.Audio(label="Output")
 
-demo = gr.Interface(fn=tts, inputs=inputs, outputs=outputs)
+
+#demo = gr.Interface(fn=tts, inputs=inputs, outputs=outputs)
 
 demo.launch()  
 gr.Interface(