Update app.py

app.py

@@ -1,6 +1,5 @@
-import gradio as gr
-from transformers import pipeline
 import torch
+from transformers import pipeline
 from datasets import load_dataset
 
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
@@ -12,18 +11,13 @@ pipe = pipeline(
   device=device,
 )
 
-pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
+ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+sample = ds[0]["audio"]
 
-def predict(input_img):
-    predictions = pipeline(input_img)
-    return input_img, {p["label"]: p["score"] for p in predictions} 
-
-gradio_app = gr.Interface(
-    predict,
-    inputs=gr.Image(label="Select hot dog candidate", sources=['upload', 'webcam'], type="pil"),
-    outputs=[gr.Image(label="Processed Image"), gr.Label(label="Result", num_top_classes=2)],
-    title="Hot Dog? Or Not?",
-)
+prediction = pipe(sample.copy(), batch_size=8)["text"]
+" Mr. Quilter is the apostle of the middle classes, and we are glad to welcome his gospel."
 
-if __name__ == "__main__":
-    gradio_app.launch()
+# we can also return timestamps for the predictions
+prediction = pipe(sample.copy(), batch_size=8, return_timestamps=True)["chunks"]
+[{'text': ' Mr. Quilter is the apostle of the middle classes and we are glad to welcome his gospel.',
+  'timestamp': (0.0, 5.44)}]