Update app.py
Browse files
app.py
CHANGED
|
@@ -40,6 +40,15 @@ def silence(duration, fps=44100):
|
|
| 40 |
Returns a silent AudioClip of the specified duration.
|
| 41 |
"""
|
| 42 |
return AudioArrayClip(np.zeros((int(fps*duration), 2)), fps=fps)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
|
| 44 |
# Define the passcode
|
| 45 |
PASSCODE = "show_feedback_db"
|
|
@@ -78,7 +87,6 @@ css = """
|
|
| 78 |
}
|
| 79 |
"""
|
| 80 |
|
| 81 |
-
|
| 82 |
# Function to save feedback or provide access to the database file
|
| 83 |
def handle_feedback(feedback):
|
| 84 |
feedback = feedback.strip() # Clean up leading/trailing whitespace
|
|
@@ -123,15 +131,14 @@ def transcribe_video(video_path):
|
|
| 123 |
start = segment["start"]
|
| 124 |
end = segment["end"]
|
| 125 |
text = segment["text"]
|
| 126 |
-
|
| 127 |
-
word_count = len(re.findall(r'\w+', text))
|
| 128 |
transcript_with_timestamps.append({
|
| 129 |
"start": start,
|
| 130 |
"end": end,
|
| 131 |
-
"text": text
|
| 132 |
-
"word_count": word_count
|
| 133 |
})
|
| 134 |
-
|
|
|
|
| 135 |
total_words += word_count
|
| 136 |
total_duration += (end - start)
|
| 137 |
|
|
|
|
| 40 |
Returns a silent AudioClip of the specified duration.
|
| 41 |
"""
|
| 42 |
return AudioArrayClip(np.zeros((int(fps*duration), 2)), fps=fps)
|
| 43 |
+
|
| 44 |
+
def count_words_or_characters(text):
|
| 45 |
+
# Count non-Chinese words
|
| 46 |
+
non_chinese_words = len(re.findall(r'\b[a-zA-Z0-9]+\b', text))
|
| 47 |
+
|
| 48 |
+
# Count Chinese characters
|
| 49 |
+
chinese_chars = len(re.findall(r'[\u4e00-\u9fff]', text))
|
| 50 |
+
|
| 51 |
+
return non_chinese_words + chinese_chars
|
| 52 |
|
| 53 |
# Define the passcode
|
| 54 |
PASSCODE = "show_feedback_db"
|
|
|
|
| 87 |
}
|
| 88 |
"""
|
| 89 |
|
|
|
|
| 90 |
# Function to save feedback or provide access to the database file
|
| 91 |
def handle_feedback(feedback):
|
| 92 |
feedback = feedback.strip() # Clean up leading/trailing whitespace
|
|
|
|
| 131 |
start = segment["start"]
|
| 132 |
end = segment["end"]
|
| 133 |
text = segment["text"]
|
| 134 |
+
|
|
|
|
| 135 |
transcript_with_timestamps.append({
|
| 136 |
"start": start,
|
| 137 |
"end": end,
|
| 138 |
+
"text": text
|
|
|
|
| 139 |
})
|
| 140 |
+
|
| 141 |
+
word_count = count_words_or_characters(text)
|
| 142 |
total_words += word_count
|
| 143 |
total_duration += (end - start)
|
| 144 |
|