Update app.py

app.py

@@ -1,22 +1,42 @@
 import gradio as gr
-from transformers import pipeline
-import numpy as np
+import whisper
+
+MODEL = whisper.load_model("base.en")
 
-transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-small.en")
 
 def transcribe(audio):
-    sr, y = audio
-    y = y.astype(np.float32)
-    y /= np.max(np.abs(y))
+    result = MODEL.transcribe(audio)
+
+    try:
+        return result["text"]
+    except:
+        return ""
+
 
-    return transcriber({"sampling_rate": sr, "raw": y})["text"]
+examples = [["apollo11_example.mp3"], ["ariane6_example.mp3"]]
 
+ui = gr.Interface(
+    fn=transcribe,
+    inputs=gr.Audio(
+        sources=["microphone", "upload"],
+        type="filepath",
+        label="Input Audio",
+    ),
+    outputs=gr.Textbox(
+        label="Transcription",
+        placeholder="The transcribed text will appear here...",
+    ),
+    title="ECHO",
+    description="""
+    This is a demo of the transcription capabilities of "ECHO". This could be adapded to run real-time transcription on a live audio stream like ISS communications.
 
-demo = gr.Interface(
-    transcribe,
-    gr.Audio(sources=["microphone"]),
-    "text",
+    ### How to use:
+    1. **Record or Upload**: Click on the microphone icon 🎙️ to record audio, usign your microphone, or click on the upload button ⬆️ to upload an audio file.
+    You can also use the **Examples** provided below, as inputs, by clicking on them.
+    2. **Click Submit**: Clicking the submit button will transcribe the audio.
+    3. **Read the Transcription**: The transcribed text will appear in the text box below the audio input section.
+    """,
+    examples=examples,
 )
 
-if __name__ == "__main__":
-    demo.launch()
+ui.launch()