Create app.py

app.py

@@ -0,0 +1,46 @@
+from transformers import pipeline
+
+asr = pipeline(task="automatic-speech-recognition",
+               model="distil-whisper/distil-small.en")
+
+# now ho to make the demo take long time audio
+def transcribe_long_form(filepath):
+    if filepath is None:
+        gr.Warning("No audio found, please retry.")
+        return ""
+    output = asr(
+      filepath,
+      max_new_tokens=256,
+      chunk_length_s=30,
+      batch_size=8,
+    )
+    return output["text"]
+
+# mic button
+mic_transcribe = gr.Interface(
+    fn=transcribe_speech,
+    inputs=gr.Audio(sources="microphone",
+                    type="filepath"),
+    outputs=gr.Textbox(label="Transcription",
+                       lines=3),
+    allow_flagging="never")
+
+# upload button
+file_transcribe = gr.Interface(
+    fn=transcribe_speech,
+    inputs=gr.Audio(sources="upload",
+                    type="filepath"),
+    outputs=gr.Textbox(label="Transcription",
+                       lines=3),
+    allow_flagging="never",
+)
+
+with demo:
+    gr.TabbedInterface(
+        [mic_transcribe,
+         file_transcribe],
+        ["Transcribe Microphone",
+         "Transcribe Audio File"],
+    )
+
+demo.launch()