Create app.py

app.py

@@ -0,0 +1,19 @@
+from speechbox import PunctuationRestorer
+from datasets import load_dataset
+
+streamed_dataset = load_dataset("librispeech_asr", "clean", split="validation", streaming=True)
+
+# get first sample
+sample = next(iter(streamed_dataset))
+
+# print out normalized transcript
+print(sample["text"])
+# => "HE WAS IN A FEVERED STATE OF MIND OWING TO THE BLIGHT HIS WIFE'S ACTION THREATENED TO CAST UPON HIS ENTIRE FUTURE"
+
+# load the restoring class
+restorer = PunctuationRestorer.from_pretrained("openai/whisper-tiny.en")
+restorer.to("cuda")
+
+restored_text, log_probs = restorer(sample["audio"]["array"], sample["text"], sampling_rate=sample["audio"]["sampling_rate"], num_beams=1)
+
+print("Restored text:\n", restored_text)