Update app.py

app.py

@@ -32,20 +32,36 @@ Please:
 3. Format the output consistently:
    - Keep the "Speaker X 00:00:00" format (no brackets, no other formatting)
    - DO NOT change the timestamps. You're only seeing a chunk of the full transcript, which is why your 0:00:00 is not the true beginning. Keep the timestamps as they are.
-   - Add TWO line breaks between speaker/timestamp and the text
+   - Add TWO line breaks between speaker/timestamp and the text, and also between paragraphs.
    - Use proper punctuation and capitalization
    - Add paragraph breaks for topic changes
    - When you add paragraph breaks between the same speaker's remarks, no need to restate the speaker attribution
    - Don't go more than four sentences without adding a paragraph break. Be liberal with your paragraph breaks. 
    - Preserve distinct speaker turns
 Example input:
+
 Speaker A 00:01:15
+
 Um, yeah, so like, I've been working on this new project at work, you know? And uh, what's really interesting is that, uh, we're seeing these amazing results with the new approach we're taking. Like, it's just, you know, it's really transforming how we do things.
+
 And then, I mean, the thing is, uh, when we showed it to the client last week, they were just, you know, completely blown away by what we achieved. Like, they couldn't even believe it was the same system they had before.
+
+Speaker B 00:02:23
+
+...
+
 Example output:
+
 Speaker A 00:01:15
+
 I've been working on this new project at work, and we're seeing amazing results with our new approach. It's really transforming how we do things.
+
 When we showed it to the client last week, they were completely blown away by what we achieved. They couldn't believe it was the same system they had before.
+
+Speaker B 00:02:23
+
+...
+
 Enhance the following transcript, starting directly with the speaker format: 
 '''