
ChatGPTã§ããã°ã©ãã³ã°ïŒ ïœããã¯ãäžçãå€ãããšïŒïŒïœ
Zoomã®æåèµ·ããããŒã¿ãåé·ãªã®ã§ã
ããã¹ãã®åœ¢åŒã倿ããããªããšæãç«ã¡
以åã ã£ãããawkãšãã§æžããã ãã©ãã¡ãã£ãšé¢å
ChatGPTã«ãé¡ãããŠã¿ãããã©ããªãïŒ
ãšã詊ããŠã¿ãããé©ãã®çµæã«ãªããŸããïœïŒ
ã¹ã¯ãªãããµã³ãã«
以äžã®ã«ãŒã«ã«åŸã£ãŠã
æ·»ä»ãã¡ã€ã«ã®ããã¹ããåŠçããPythonã®ããã°ã©ã ãçæããäžã§ã
åŠççµæãããã¹ããã¡ã€ã«åœ¢åŒã§ä¿åããŠãã ããã
##å ¥åäŸïŒ
1
00:00:03.440 --> 00:00:04.960
å·åèæš¹ïŒ æªæ¥å®çŸããŒãããŒ: ã¯ãŒãã
##åºåäŸïŒ
00:00:03 å·å ã¯ãŒãã
##å ¥åäŸïŒ
3140
02:48:14.930 --> 02:48:15.500
xxx: ãã£ã±ã
##åºåäŸïŒ
02:48:14 xxx ãã£ã±ã
##ãã®ä»ã®ã«ãŒã«
ã»ç©ºçœè¡ïŒã¹ããŒã¹ã®ã¿ãå«ãïŒã¯åé€ãã
ã»æ°åã ãã®è¡ãåé€ãã
ã»åºåã¯ã¿ãïŒ\tïŒã§åºåããïŒè¡ã«ãŸãšãã
æç€ºããã®ã¯ããããªæã
空çœè¡ãå«ããŠïŒè¡ã§ïŒã»ããã®éšåã
ïŒè¡ã§ã·ã³ãã«ã«ãŸãšããåŠçã§ã
åé ã«ããã£ãŠã»ããããšã®å šäœåã瀺ã
Pythonã®ããã°ã©ã ãçæãã
å®è¡ããŠã
çµæããã¡ã€ã«ã§åºåãã
åŠçå
å®¹ã®æç€ºã¯ã
å
¥åãšåºåã察æ¯ããŠããµã³ãã«ãïŒã€äžããã ã
å
·äœçã«ãäœãã©ããããã¯ãæç€ºããŠããªã
ããããåŸæ¥ã®ããã°ã©ãã³ã°ãšå€§ããéããšãã
ãã®ä»ã®ã«ãŒã«ã¯ç®æ¡æžãã§
æãã€ããŸãŸãé©åœã«
人éã®éšäžã«æç€ºããã¿ããã§ãã
çæãããããã°ã©ã
import re
def process_transcript(input_file, output_file):
with open(input_file, 'r', encoding='utf-8') as file:
lines = file.readlines()
output_lines = []
timestamp = ""
speaker = ""
content = ""
for line in lines:
line = line.strip()
if not line or line.isdigit():
continue # 空çœè¡ãŸãã¯æ°åã®ã¿ã®è¡ãã¹ããã
timestamp_match = re.match(r"(\d{2}:\d{2}:\d{2})\.\d{3} -->", line)
if timestamp_match:
timestamp = timestamp_match.group(1) # ã¿ã€ã ã¹ã¿ã³ããæœåº
continue
speaker_match = re.match(r"([^:]+): (.+)", line)
if speaker_match:
speaker = speaker_match.group(1).split('ïŒ ')[0] # ã¹ããŒã«ãŒåãïŒ åã§åãåã
content = speaker_match.group(2) # çºèšå 容ãååŸ
output_lines.append(f"{timestamp}\t{speaker}\t{content}")
with open(output_file, 'w', encoding='utf-8') as file:
file.write("\n".join(output_lines))
# ãã¡ã€ã«åèšå®
input_filename = "/mnt/data/Recording.transcript.txt"
output_filename = "/mnt/data/processed_transcript.txt"
# ã¹ã¯ãªããå®è¡
process_transcript(input_filename, output_filename)
print(f"åŠçãå®äºããŸãããåºåãã¡ã€ã«: {output_filename}")
ç§ã¯ãPython䜿ã£ãããšãªãã§ãããçŸããã³ãŒãã§ããïœ
èªã¿ããããã ããç¡ã
ã¡ãããšã³ã¡ã³ããå ¥ããŠãããŠãã
ããŒã¿ã®æå³ãæç€ºããŠãªãã®ã«ãã¡ãããšèªèããŠãã
ã¿ã€ã ã¹ã¿ã³ããçºèšè ãå 容ããšïŒ
æååŠçã¯ããããïŒ
æ£èŠè¡šçŸã§ããã£ãããš
ããã¯ãããã¯ãªã§ãïŒ
ãã®ãããã®ç°¡åãªããã°ã©ãã³ã°ã§ã¯ã
人éã®åºçªããã³ãã«ç¡ããªããã
ãããŠãããã°ã©ã å®è¡ãšãã¡ã€ã«åºåãŸã§ãäžæ°ã«ãã£ãŠãããŠ
åŠççµæãããããªã§ããïŒ
æãã€ããŠããããããŸã§ã
ïŒåãããã£ãŠããŸãã
ç§ããã£ããããŸãïŒæ¥ããã£ãŠãããããã°ãŸã§çµãããªãããðŠ
ïŒãããªæéãªããã©ïœïŒ
ããã¯ãäžçãå€ãããªãïœïŒ
å°åŠçã§ããããã°ã©ãã³ã°ã§ããïŒïŒ
ã©ãã©ããAIã§åºæ¥ãããšãå¢ããŠããŸã
ããå°ããè²ã
ãã©ã€ããŠã¿ãããªããŸããïœ ^^)/
ãã®èšäºãæžããã®ã¯ã
åçã®æ±ãå¢ãããæªæ¥å®çŸããŒãããŒããå·åèæš¹
https://mousoubiz.com/
https://twitter.com/mousoubiz