Initial Draft

voice.py

@@ -7,12 +7,12 @@ import scipy
 ############################
 
 # -- UI Variables
-ui_input_type=gr.Dropdown(
+ui_input_voice_preseter=gr.Dropdown(
     ["v2/en_speaker_0","v2/en_speaker_9"], label="Voice Presenter"
 )
-ui_input_filename=gr.Textbox(label="wav filename")
+ui_input_filename=gr.Textbox(label="Input WAV Filename")
 ui_input_text=gr.Textbox(lines=22,label="Input Text")
-ui_output=gr.Textbox(lines=22,label="Output")
+ui_output=gr.Audio(label="Output")
 
 # -- Model Variables
 processor = AutoProcessor.from_pretrained("suno/bark")
@@ -23,10 +23,34 @@ model = BarkModel.from_pretrained("suno/bark")
 ############################
 
 # -- On Click of Submit Button in UI
-def submit(type, input_text):
-   ui_output=""
+def submit(voice_preseter, filename, input_text):
+   print("Hello World")
    
+    inputs = processor(input_text, voice_preset=voice_preseter) 
+   audio_array = model.generate(**inputs)
+   audio_array = audio_array.cpu().numpy().squeeze() 
+   sample_rate = model.generation_config.sample_rate
+   scipy.io.wavfile.write(filename, rate=sample_rate, data=audio_array) 
+   
+   retun gr.Audio(source=[os.path.join(os.path.dirname(__file__),filename)     
 
 ############################
 ###### Main Program ########
-############################
+############################
+ui_input_filename = "Hello uh ... [clears throat], \
+        Bark is a transformer-based text-to-speech model proposed by Suno AI. \
+        This voice is auto generated"
+
+# -- Start of Program - Main
+def main():
+    demo = gr.Interface(
+                        fn=submit, 
+                        inputs=[ui_input_voice_preseter,ui_input_filename,ui_input_text], 
+                        outputs=ui_output,
+                        allow_flagging="never"
+                    ) 
+    demo.queue().launch()
+
+# -- Calling Main Function
+if __name__ == '__main__':
+    main()