Changed to simplified implementation of audioldm

app.py

@@ -1,8 +1,20 @@
 import gradio as gr
 
-def greet(name):
-    return ("hello" + name)
+from diffusers import AudioLDMPipeline
+import torch
+# import scipy
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
+repo_id = "cvssp/audioldm-s-full-v2"
+pipe = AudioLDMPipeline.from_pretrained(repo_id, torch_dtype=torch.float32)
+pipe = pipe.to("cpu")
+
+def texttoaudio(prompt):
+    audio = pipe(prompt, num_inference_steps=10, audio_length_in_s=5.0).audios[0]
+
+    # save the audio sample as a .wav file
+    # scipy.io.wavfile.write("output.wav", rate=16000, data=audio)
+    return (rate=16000, data=audio)
+
+iface = gr.Interface(fn=texttoaudio, inputs="text", outputs="audio")
 
 iface.launch()