Create app.py

app.py

@@ -0,0 +1,35 @@
+from transformers import pipeline
+import torch
+import gradio as gr
+
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
+
+pipe = pipeline(
+    "automatic-speech-recognition",
+    model="openai/whisper-small.en",
+    chunk_length_s=30,
+    device=device,
+)
+
+# Function to transcribe audio
+def transcribe(audio):
+    text = pipe(audio)["text"]
+    return text
+
+# Gradio components
+audio_input = gr.Audio(sources=["microphone"], type="filepath", label="Record Audio")
+text_output = gr.Textbox(label="Transcription")
+submit_button = gr.Button("Transcribe")
+
+# Create the interface
+with gr.Blocks() as demo:
+    with gr.Row():
+        audio_input.render()
+        submit_button.render()
+    with gr.Row():
+        text_output.render()
+
+    submit_button.click(fn=transcribe, inputs=audio_input, outputs=text_output)
+
+
+demo.launch()