woncomp/malabar
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

skip translating opening song

Browse Source
This commit is contained in:
Joshua Zhang
2026-03-04 13:18:35 +08:00
parent 18eae970ad
commit e085eeddbc
1 changed files with 12 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
step4_translate.py
View File

@@ -238,10 +238,19 @@ def translate_file(input_path: Path, client: OpenAI, model: str) -> Path:
# Check cache for each line # Check cache for each line
cached_count = 0 cached_count = 0
skipped_count = 0
to_translate = [] to_translate = []
for line_data in parsed_lines: for line_data in parsed_lines:
english = line_data["english"] english = line_data["english"]
speaker = line_data["speaker"]
# Skip translation for opening song (speaker is "Song")
if speaker == "Song":
line_data["chinese"] = english # Keep English for song lyrics
skipped_count += 1
continue
cached = get_cached_translation(english) cached = get_cached_translation(english)
if cached: if cached:
line_data["chinese"] = cached line_data["chinese"] = cached
@@ -250,6 +259,7 @@ def translate_file(input_path: Path, client: OpenAI, model: str) -> Path:
to_translate.append(line_data) to_translate.append(line_data)
print(f" Cached translations: {cached_count}") print(f" Cached translations: {cached_count}")
print(f" Skipped (Song): {skipped_count}")
print(f" To translate: {len(to_translate)}") print(f" To translate: {len(to_translate)}")
# Translate in batches # Translate in batches
@@ -274,10 +284,10 @@ def translate_file(input_path: Path, client: OpenAI, model: str) -> Path:
if translation and translation != "[Translation failed]": if translation and translation != "[Translation failed]":
save_translation_cache(line_data["english"], translation) save_translation_cache(line_data["english"], translation)
# Combine results (cached + translated) # Combine results (cached + translated + skipped)
result = parsed_lines result = parsed_lines
print(f" Translation complete: {cached_count} from cache, {translated_count} new") print(f" Translation complete: {cached_count} from cache, {translated_count} new, {skipped_count} skipped (Song)")
# Save JSON output # Save JSON output
output_filename = input_path.stem.replace("_speakers", "") + "_translated.json" output_filename = input_path.stem.replace("_speakers", "") + "_translated.json"