Update app.py

app.py

@@ -9,6 +9,22 @@ model = whisper.load_model("base")
 # model = pipeline(model="AlexMo/FIFA_WC22_WINNER_LANGUAGE_MODEL")
 summarizer = pipeline("summarization")
 
+def transcribe(microphone, file_upload):
+    warn_output = ""
+    if (microphone is not None) and (file_upload is not None):
+        warn_output = (
+            "WARNING: You've uploaded an audio file and used the microphone. "
+            "The recorded file from the microphone will be used and the uploaded audio will be discarded.\n"
+        )
+
+    elif (microphone is None) and (file_upload is None):
+        return "ERROR: You have to either use the microphone or upload an audio file"
+
+    file = microphone if microphone is not None else file_upload
+
+    text = summarizer(file)["text"]
+
+    return warn_output + text
 
 def getAudio(url):
     link = YouTube(url)
@@ -36,23 +52,45 @@ def getSummary(article):
 
 
 with gr.Blocks() as demo:
-    gr.Markdown(
-        "<h1><center>Free Fast YouTube URL Video to Text using <a href=https://openai.com/blog/whisper/ target=_blank>OpenAI's Whisper</a> Model</center></h1>")
-    gr.Markdown(
-        "<center>Enter the link of any YouTube video to generate a text transcript of the video and then create a summary of the video transcript.</center>")
-    gr.Markdown(
-        "<center><b>'Whisper is a neural net that approaches human level robustness and accuracy on English speech recognition.'</b></center>")
-    gr.Markdown(
-        "<center>Generating the transcript takes 5-10 seconds per minute of the video</center>")
-
-    input_text_url = gr.Textbox(placeholder='Youtube video URL', label='URL')
-    result_button_transcribe = gr.Button('1. Transcribe')
-    output_text_transcribe = gr.Textbox(placeholder='Transcript of the YouTube video.', label='Transcript')
-
-    result_button_summary = gr.Button('2. Create Summary')
-    output_text_summary = gr.Textbox(placeholder='Summary of the YouTube video transcript.', label='Summary')
-
-    result_button_transcribe.click(getText, inputs=input_text_url, outputs=output_text_transcribe)
-    result_button_summary.click(getSummary, inputs=output_text_transcribe, outputs=output_text_summary)
+    gr.HTML(
+        """
+            <div style="text-align: center; max-width: 500px; margin: 0 auto;">
+              <div>
+                <h1>Dutch whisperer</h1>
+              </div>
+              <p style="margin-bottom: 10px; font-size: 94%">
+                Summarize audio files, mic input or Youtube videos using OpenAI's Whisper
+              </p>
+            </div>
+        """
+    )
+    with gr.Tab('Get a summary from your own mic or audio file'):
+        with gr.Row():
+            gr.Interface(
+                fn=transcribe,
+                inputs=[
+                    gr.inputs.Audio(source="microphone", type="filepath", optional=True),
+                    gr.inputs.Audio(source="upload", type="filepath", optional=True),
+                ],
+                outputs="text",
+                layout="horizontal",
+                theme="huggingface",
+                title="Dutch whisper: Summarize Audio",
+                description=(
+                    "Transcribe and summarize."
+                ),
+                allow_flagging="never",
+            )
+    with gr.Tab('Summary of Youtube video'):
+        with gr.Row():
+            input_text_url = gr.Textbox(placeholder='Youtube video URL', label='URL')
+            result_button_transcribe = gr.Button('1. Transcribe')
+            output_text_transcribe = gr.Textbox(placeholder='Transcript of the YouTube video.', label='Transcript')
+
+            result_button_summary = gr.Button('2. Create Summary')
+            output_text_summary = gr.Textbox(placeholder='Summary of the YouTube video transcript.', label='Summary')
+
+            result_button_transcribe.click(getText, inputs=input_text_url, outputs=output_text_transcribe)
+            result_button_summary.click(getSummary, inputs=output_text_transcribe, outputs=output_text_summary)
 
 demo.launch(debug=True)