Update app.py

app.py

@@ -1,23 +1,34 @@
+import gradio as gr
 import torch
 from transformers import pipeline
 from datasets import load_dataset
 
-device = "cuda:0" if torch.cuda.is_available() else "cpu"
+# device = "cuda:0" if torch.cuda.is_available() else "cpu"
 
-pipe = pipeline(
+# ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+# sample = ds[0]["audio"]
+
+def transcribe_audio(sample):
+ pipe = pipeline(
   "automatic-speech-recognition",
   model="openai/whisper-small",
   chunk_length_s=30,
-  device=device,
-)
-
-ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
-sample = ds[0]["audio"]
+ )
+#  prediction = pipe(sample.copy(), batch_size=8)["text"]
+ prediction = pipe(sample.copy(), batch_size=8, return_timestamps=True)["chunks"]
+ return prediction
 
-prediction = pipe(sample.copy(), batch_size=8)["text"]
+# we can also return timestamps for the predictions
+ 
 
 
-# we can also return timestamps for the predictions
-prediction = pipe(sample.copy(), batch_size=8, return_timestamps=True)["chunks"]
+interface = gr.Interface(
+    fn=transcribe_audio,  # The function to be applied to the audio input
+    inputs=gr.Audio(type="filepath"),  # Users can record or upload audio
+    outputs="text",  # The output is the transcription (text)
+    title="Whisper Small ASR",  # Title of your app
+    description="Transcription using Whisper Small."  # Description of your app
+)
 
-print(prediction[0]['text'])
+# **This line starts the Gradio app**
+interface.launch()