Update app.py

app.py

@@ -21,11 +21,16 @@ def format_output_to_list(data):
     formatted_list = "\n".join([f"{item['timestamp'][0]}s - {item['timestamp'][1]}s \t : {item['text']}" for item in data])
     return formatted_list
 
-def transcribe(inputs, task):
+def transcribe(inputs, task, timestamp_type):
     if inputs is None:
         raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")
 
-    output = pipe(inputs, batch_size=BATCH_SIZE, return_timestamps="word", generate_kwargs={"task": task})
+    if timestamp_type == "sentence":
+        timestamp_type = True
+    else:
+        timestamp_type = "word"
+
+    output = pipe(inputs, batch_size=BATCH_SIZE, return_timestamps=timestamp_type, generate_kwargs={"task": task})
     text = output['text']
     timestamps = format_output_to_list(output['chunks'])
     return  [text, timestamps]
@@ -47,24 +52,25 @@ examples = [
     ]
 
 with gr.Blocks(theme=gr.themes.Default()) as demo:
-    gr.HTML("<h1 style='text-align: center;'>Transcribe Audio with Timestamps using whisper-large-v3</h1>")
+    gr.HTML("<h2 style='text-align: center;'>Transcribing Audio with Timestamps using whisper-large-v3</h2>")
     gr.Markdown("")
     with gr.Row():
         with gr.Column():
             audio_input = gr.Audio(sources=["upload", 'microphone'], type="filepath", label="Audio file")
             task = gr.Radio(["transcribe", "translate"], label="Task")
+            timestamp_type = gr.Radio(["sentence", "word"], label="Timestamp Type")
             with gr.Row():
                 clear_button = gr.ClearButton(value="Clear")
                 submit_button = gr.Button("Submit", variant="primary", )
             
         with gr.Column():
             transcript_output = gr.Text(label="Transcript")
-            timestamp_output = gr.Text(label="Timestamp")
+            timestamp_output = gr.Text(label="Timestamps")
     
-    examples = gr.Examples(examples, inputs=audio_input, outputs=[transcript_output, timestamp_output], fn=transcribe, examples_per_page=20)
+    examples = gr.Examples(examples, inputs=[audio_input, task, timestamp_type], outputs=[transcript_output, timestamp_output], fn=transcribe, examples_per_page=20)
 
-    submit_button.click(fn=transcribe, inputs=audio_input, outputs=[transcript_output, timestamp_output])
-    clear_button.add([audio_input, transcript_output, timestamp_output])
+    submit_button.click(fn=transcribe, inputs=[audio_input, task, timestamp_type], outputs=[transcript_output, timestamp_output])
+    clear_button.add([audio_input, task, timestamp_type, transcript_output, timestamp_output])
 
 
 if __name__ == "__main__":