add more examples

app.py

@@ -98,7 +98,7 @@ def predict(audio_path):
     audio_inputs = librosa.resample(audio_data, orig_sr=sr, target_sr=pipe.feature_extractor.sampling_rate)
     output = pipe(audio_inputs, chunk_length_s=30, stride_length_s=[4, 2], return_timestamps="word")
     chunks = output["chunks"]
-    print(chunks)
+    #print(chunks)
 
     # Create the video.
     clip = mpy.VideoClip(make_frame, duration=duration)
@@ -123,6 +123,8 @@ article = """
 
 <ul>
 <li>Shakespeare's "Henry V" speech from <a href="https://freesound.org/people/acclivity/sounds/24096/">acclivity</a> (CC BY-NC 4.0 license)
+<li>"Here's to the Crazy Ones" speech by Steve Jobs</li>
+<li>"Stupid People" comedy routine by Bill Engvall</li>
 <li>Lato font by Łukasz Dziedzic (licensed under Open Font License)</li>
 <li>Whisper model by OpenAI</li>
 </ul>
@@ -131,7 +133,9 @@ article = """
 """
 
 examples = [
+    "examples/steve_jobs_crazy_ones.mp3",
     "examples/henry5.wav",
+    "examples/stupid_people.mp3",
 ]
 
 gr.Interface(

examples/steve_jobs_crazy_ones.mp3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adc4eb3004ef2878dd694a893ec9cd0c1e2ccc749f8a47aaf4d7fdbdad33cb42
+size 1467173

examples/stupid_people.mp3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b91f0d180d32a75bc911a22b9331c60b70200087df16e6a422d949e669606ec8
+size 498736