Spaces:
Paused
Paused
Update app.py
Browse files
app.py
CHANGED
|
@@ -58,26 +58,27 @@ def process_video(Video, target_language):
|
|
| 58 |
with open(transcript_file, "w+", encoding="utf-8") as f:
|
| 59 |
counter = 1
|
| 60 |
for line in transcript_with_timestamps:
|
| 61 |
-
#
|
| 62 |
-
|
| 63 |
-
|
|
|
|
| 64 |
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
# Write to SRT file
|
| 70 |
-
f.write(f"{counter}\n")
|
| 71 |
-
f.write(f"{formatted_start} --> {formatted_end}\n")
|
| 72 |
-
f.write(f"{word}\n\n")
|
| 73 |
-
counter += 1
|
| 74 |
-
|
| 75 |
-
|
| 76 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
# Move the file pointer to the beginning of the file.
|
| 78 |
f.seek(0)
|
| 79 |
|
| 80 |
-
# Translating the SRT from Whisper with
|
| 81 |
target_language_code = google_lang_codes.get(target_language, "en")
|
| 82 |
paragraph = ""
|
| 83 |
for line in f:
|
|
|
|
| 58 |
with open(transcript_file, "w+", encoding="utf-8") as f:
|
| 59 |
counter = 1
|
| 60 |
for line in transcript_with_timestamps:
|
| 61 |
+
# Use a regular expression to extract timestamp and word from the line
|
| 62 |
+
match = re.match(r"\[(.*?)s -> (.*?)s\] (.*)", line)
|
| 63 |
+
if match:
|
| 64 |
+
start_time, end_time, word = match.groups()
|
| 65 |
|
| 66 |
+
# Convert timestamps to SRT format
|
| 67 |
+
formatted_start = str(datetime.timedelta(seconds=float(start_time)))
|
| 68 |
+
formatted_end = str(datetime.timedelta(seconds=float(end_time)))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
|
| 70 |
+
# Write to SRT file
|
| 71 |
+
f.write(f"{counter}\n")
|
| 72 |
+
f.write(f"{formatted_start} --> {formatted_end}\n")
|
| 73 |
+
f.write(f"{word}\n\n")
|
| 74 |
+
counter += 1
|
| 75 |
+
else:
|
| 76 |
+
# Handle the case where the line does not match the pattern
|
| 77 |
+
print(f"Line does not match expected format: {line}")
|
| 78 |
# Move the file pointer to the beginning of the file.
|
| 79 |
f.seek(0)
|
| 80 |
|
| 81 |
+
# Translating the SRT from Whisper with Google Translate.
|
| 82 |
target_language_code = google_lang_codes.get(target_language, "en")
|
| 83 |
paragraph = ""
|
| 84 |
for line in f:
|