Update app.py

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 import torch
-
+from datasets import load_dataset
 from diffusers import DiffusionPipeline
 from transformers import (
     WhisperForConditionalGeneration,
@@ -27,6 +27,15 @@ diffuser_pipeline = DiffusionPipeline.from_pretrained(
 diffuser_pipeline.enable_attention_slicing()
 diffuser_pipeline = diffuser_pipeline.to(device)
 
+#————————————————————————————————————————————
+# TESTING WITH DATASET
+ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+
+audio_sample = ds[3]
+
+text = audio_sample["text"].lower()
+speech_data = audio_sample["audio"]["array"]
+
 #————————————————————————————————————————————
 # GRADIO SETUP
 title = "Speech to Diffusion • Community Pipeline"
@@ -51,8 +60,8 @@ def speech_to_text(audio_sample):
   ————————
   """)
   
-  output = diffuser_pipeline(audio_sample[1])
-  
+  #output = diffuser_pipeline(audio_sample[1])
+  output = diffuser_pipeline(speech_data)
   print(f"""
   ————————
   output: {output}