Update app.py

app.py

@@ -1,48 +1,19 @@
 import gradio as gr
-from pydub import AudioSegment
-from time import sleep
+from transformers import pipeline
+import numpy as np
 
-with gr.Blocks() as demo:
-    input_audio = gr.Audio(label="Input Audio", type="filepath", format="mp3")
-    with gr.Row():
-        with gr.Column():
-            stream_as_file_btn = gr.Button("Stream as File")
-            format = gr.Radio(["wav", "mp3"], value="wav", label="Format")
-            stream_as_file_output = gr.Audio(streaming=True)
+transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")
 
-            def stream_file(audio_file, format):
-                audio = AudioSegment.from_file(audio_file)
-                i = 0
-                chunk_size = 1000
-                while chunk_size * i < len(audio):
-                    chunk = audio[chunk_size * i : chunk_size * (i + 1)]
-                    i += 1
-                    if chunk:
-                        file = f"/tmp/{i}.{format}"
-                        chunk.export(file, format=format)
-                        yield file
-                        sleep(0.5)
+def transcribe(audio):
+    sr, y = audio
+    y = y.astype(np.float32)
+    y /= np.max(np.abs(y))
 
-            stream_as_file_btn.click(
-                stream_file, [input_audio, format], stream_as_file_output
-            )
+    return transcriber({"sampling_rate": sr, "raw": y})["text"]
 
 
-        with gr.Column():
-            stream_as_bytes_btn = gr.Button("Stream as Bytes")
-            stream_as_bytes_output = gr.Audio(format="bytes", streaming=True)
+demo = gr.Interface(
+    fn=transcribe, inputs=gr.Audio(sources="microphone", type="filepath"), outputs=gr.outputsText()
+)
 
-            def stream_bytes(audio_file):
-                chunk_size = 20_000
-                with open(audio_file, "rb") as f:
-                    while True:
-                        chunk = f.read(chunk_size)
-                        if chunk:
-                            yield chunk
-                            sleep(1)
-                        else:
-                            break
-            stream_as_bytes_btn.click(stream_bytes, input_audio, stream_as_bytes_output)
-
-if __name__ == "__main__":
-    demo.queue().launch()
+demo.launch()