Update generate_audio.py

generate_audio.py

@@ -116,8 +116,8 @@ class TTSGenerator:
         # audio_arr = speech_output[0].cpu().numpy()
         # return audio_arr, self.bark_sampling_rate
         # Tokenize input text and obtain input IDs and attention mask
-        inputs = bark_processor(text, voice_preset="v2/en_speaker_6").to(device)
-        speech_output = bark_model.generate(**inputs, temperature=0.9, semantic_temperature=0.8)
+        inputs = self.bark_processor(text, voice_preset="v2/en_speaker_6").to(device)
+        speech_output = self.bark_model.generate(**inputs, temperature=0.9, semantic_temperature=0.8)
         audio_arr = speech_output[0].cpu().numpy()
         return audio_arr, self.bark_sampling_rate