Commit

app.py

@@ -68,15 +68,15 @@ print(caption)
 translated_caption = translate(caption)
 print(translated_caption)
 
-# Generate Audio
-inputs = audio_processor(
-    text=caption,
-    return_tensors="pt",
-)
-
-speech_values = audio_model.generate(**inputs, do_sample=True)
-
-sampling_rate = audio_model.generation_config.sample_rate
-Audio(speech_values.cpu().numpy().squeeze(), rate=sampling_rate)
+# # Generate Audio
+# inputs = audio_processor(
+#     text=caption,
+#     return_tensors="pt",
+# )
+#
+# speech_values = audio_model.generate(**inputs, do_sample=True)
+#
+# sampling_rate = audio_model.generation_config.sample_rate
+# Audio(speech_values.cpu().numpy().squeeze(), rate=sampling_rate)