367 lines
15 KiB
Python
367 lines
15 KiB
Python
import json
|
||
from core.utils import *
|
||
|
||
## ================================================================
|
||
# @ step4_splitbymeaning.py
|
||
def get_split_prompt(sentence, num_parts = 2, word_limit = 20):
|
||
language = load_key("whisper.detected_language")
|
||
split_prompt = f"""
|
||
## Role
|
||
You are a professional Netflix subtitle splitter in **{language}**.
|
||
|
||
## Task
|
||
Split the given subtitle text into **{num_parts}** parts, each less than **{word_limit}** words.
|
||
|
||
1. Maintain sentence meaning coherence according to Netflix subtitle standards
|
||
2. MOST IMPORTANT: Keep parts roughly equal in length (minimum 3 words each)
|
||
3. Split at natural points like punctuation marks or conjunctions
|
||
4. If provided text is repeated words, simply split at the middle of the repeated words.
|
||
|
||
## Steps
|
||
1. Analyze the sentence structure, complexity, and key splitting challenges
|
||
2. Generate two alternative splitting approaches with [br] tags at split positions
|
||
3. Compare both approaches highlighting their strengths and weaknesses
|
||
4. Choose the best splitting approach
|
||
|
||
## Given Text
|
||
<split_this_sentence>
|
||
{sentence}
|
||
</split_this_sentence>
|
||
|
||
## Output in only JSON format and no other text
|
||
```json
|
||
{{
|
||
"analysis": "Brief description of sentence structure, complexity, and key splitting challenges",
|
||
"split1": "First splitting approach with [br] tags at split positions",
|
||
"split2": "Alternative splitting approach with [br] tags at split positions",
|
||
"assess": "Comparison of both approaches highlighting their strengths and weaknesses",
|
||
"choice": "1 or 2"
|
||
}}
|
||
```
|
||
|
||
Note: Start you answer with ```json and end with ```, do not add any other text.
|
||
""".strip()
|
||
return split_prompt
|
||
|
||
"""{{
|
||
"analysis": "Brief analysis of the text structure",
|
||
"split": "Complete sentence with [br] tags at split positions"
|
||
}}"""
|
||
|
||
## ================================================================
|
||
# @ step4_1_summarize.py
|
||
def get_summary_prompt(source_content, custom_terms_json=None):
|
||
src_lang = load_key("whisper.detected_language")
|
||
tgt_lang = load_key("target_language")
|
||
|
||
# add custom terms note
|
||
terms_note = ""
|
||
if custom_terms_json:
|
||
terms_list = []
|
||
for term in custom_terms_json['terms']:
|
||
terms_list.append(f"- {term['src']}: {term['tgt']} ({term['note']})")
|
||
terms_note = "\n### Existing Terms\nPlease exclude these terms in your extraction:\n" + "\n".join(terms_list)
|
||
|
||
summary_prompt = f"""
|
||
## Role
|
||
You are a video translation expert and terminology consultant, specializing in {src_lang} comprehension and {tgt_lang} expression optimization.
|
||
|
||
## Task
|
||
For the provided {src_lang} video text:
|
||
1. Summarize main topic in two sentences
|
||
2. Extract professional terms/names with {tgt_lang} translations (excluding existing terms)
|
||
3. Provide brief explanation for each term
|
||
|
||
{terms_note}
|
||
|
||
Steps:
|
||
1. Topic Summary:
|
||
- Quick scan for general understanding
|
||
- Write two sentences: first for main topic, second for key point
|
||
2. Term Extraction:
|
||
- Mark professional terms and names (excluding those listed in Existing Terms)
|
||
- Provide {tgt_lang} translation or keep original
|
||
- Add brief explanation
|
||
- Extract less than 15 terms
|
||
|
||
## INPUT
|
||
<text>
|
||
{source_content}
|
||
</text>
|
||
|
||
## Output in only JSON format and no other text
|
||
{{
|
||
"theme": "Two-sentence video summary",
|
||
"terms": [
|
||
{{
|
||
"src": "{src_lang} term",
|
||
"tgt": "{tgt_lang} translation or original",
|
||
"note": "Brief explanation"
|
||
}},
|
||
...
|
||
]
|
||
}}
|
||
|
||
## Example
|
||
{{
|
||
"theme": "本视频介绍人工智能在医疗领域的应用现状。重点展示了AI在医学影像诊断和药物研发中的突破性进展。",
|
||
"terms": [
|
||
{{
|
||
"src": "Machine Learning",
|
||
"tgt": "机器学习",
|
||
"note": "AI的核心技术，通过数据训练实现智能决策"
|
||
}},
|
||
{{
|
||
"src": "CNN",
|
||
"tgt": "CNN",
|
||
"note": "卷积神经网络，用于医学图像识别的深度学习模型"
|
||
}}
|
||
]
|
||
}}
|
||
|
||
Note: Start you answer with ```json and end with ```, do not add any other text.
|
||
""".strip()
|
||
return summary_prompt
|
||
|
||
## ================================================================
|
||
# @ step5_translate.py & translate_lines.py
|
||
def generate_shared_prompt(previous_content_prompt, after_content_prompt, summary_prompt, things_to_note_prompt):
|
||
return f'''### Context Information
|
||
<previous_content>
|
||
{previous_content_prompt}
|
||
</previous_content>
|
||
|
||
<subsequent_content>
|
||
{after_content_prompt}
|
||
</subsequent_content>
|
||
|
||
### Content Summary
|
||
{summary_prompt}
|
||
|
||
### Points to Note
|
||
{things_to_note_prompt}'''
|
||
|
||
def get_prompt_faithfulness(lines, shared_prompt):
|
||
TARGET_LANGUAGE = load_key("target_language")
|
||
# Split lines by \n
|
||
line_splits = lines.split('\n')
|
||
|
||
json_dict = {}
|
||
for i, line in enumerate(line_splits, 1):
|
||
json_dict[f"{i}"] = {"origin": line, "direct": f"direct {TARGET_LANGUAGE} translation {i}."}
|
||
json_format = json.dumps(json_dict, indent=2, ensure_ascii=False)
|
||
|
||
src_language = load_key("whisper.detected_language")
|
||
prompt_faithfulness = f'''
|
||
## Role
|
||
You are a professional Netflix subtitle translator, fluent in both {src_language} and {TARGET_LANGUAGE}, as well as their respective cultures.
|
||
Your expertise lies in accurately understanding the semantics and structure of the original {src_language} text and faithfully translating it into {TARGET_LANGUAGE} while preserving the original meaning.
|
||
|
||
## Task
|
||
We have a segment of original {src_language} subtitles that need to be directly translated into {TARGET_LANGUAGE}. These subtitles come from a specific context and may contain specific themes and terminology.
|
||
|
||
1. Translate the original {src_language} subtitles into {TARGET_LANGUAGE} line by line
|
||
2. Ensure the translation is faithful to the original, accurately conveying the original meaning
|
||
3. Consider the context and professional terminology
|
||
|
||
{shared_prompt}
|
||
|
||
<translation_principles>
|
||
1. Faithful to the original: Accurately convey the content and meaning of the original text, without arbitrarily changing, adding, or omitting content.
|
||
2. Accurate terminology: Use professional terms correctly and maintain consistency in terminology.
|
||
3. Understand the context: Fully comprehend and reflect the background and contextual relationships of the text.
|
||
</translation_principles>
|
||
|
||
## INPUT
|
||
<subtitles>
|
||
{lines}
|
||
</subtitles>
|
||
|
||
## Output in only JSON format and no other text
|
||
```json
|
||
{json_format}
|
||
```
|
||
|
||
Note: Start you answer with ```json and end with ```, do not add any other text.
|
||
'''
|
||
return prompt_faithfulness.strip()
|
||
|
||
|
||
def get_prompt_expressiveness(faithfulness_result, lines, shared_prompt):
|
||
TARGET_LANGUAGE = load_key("target_language")
|
||
json_format = {
|
||
key: {
|
||
"origin": value["origin"],
|
||
"direct": value["direct"],
|
||
"reflect": "your reflection on direct translation",
|
||
"free": "your free translation"
|
||
}
|
||
for key, value in faithfulness_result.items()
|
||
}
|
||
json_format = json.dumps(json_format, indent=2, ensure_ascii=False)
|
||
|
||
src_language = load_key("whisper.detected_language")
|
||
prompt_expressiveness_v2 = f'''
|
||
## Role
|
||
You're not just a translator—you're the script's hype man! As a Dubbing Script Wizard for Netflix-level binges, your gig is to turn stiff translations into laugh-out-loud, perfectly timed voice-overs that feel like your best mate just told you the tea. Think stand-up comic meets timing ninja—no boring textbook stuff allowed!
|
||
|
||
## Core Mission: Time-Synchronized Script Adaptation (With Flair!)
|
||
We've got a literal translation from {src_language} to {TARGET_LANGUAGE}. Your mission? Make it snappy, hilarious, and timed to the millisecond—so viewers go, "Whoa, this dubbed version slaps harder than the original!" Ditch the robotic vibe; we want casual, cheeky, and oh-so-relatable.
|
||
|
||
## The Non-Negotiable Constraint: The Time Budget (Keep It Tight, Keep It Fun)
|
||
Here's the kicker: Chinese rambles, English zips. A direct translation? Always too long. Your #1 job is to **aggressively slash and spice up** the text so it fits the original {src_language} audio's timing—like fitting a joke into a TikTok clip. Shorter isn't just better; it's mandatory. But don't just cut words—add personality! Rewrite like you're texting your homie, not drafting a legal doc.
|
||
|
||
## Guiding Principles for Adaptation (Make It Pop!):
|
||
1. **Triage with a Grin:** For each line, grab the core vibe (the "aha!" moment). Keep it sacred. Ditch secondary fluff unless it's funny—then maybe sneak it in as a wink. If timing's tight, axe it like, "Nah, we good."
|
||
2. **Rewrite Like You're Roasting:** Forget the literal translation's structure. Get the gist, then spit it out in the most natural {TARGET_LANGUAGE} slang possible. Swap "It is imperative" for "Yo, you gotta!"—make it sound like a pub chat, not a lecture.
|
||
3. **Sound Like a Real Human (With Jokes on Deck):** Use "gonna," "wanna," and contractions like they're going out of style. Add a light-hearted jab or a sassy quip where it fits—but keep it smooth, not forced. Read it in your head: if it doesn't make you smirk, scrap it and try again with a grin.
|
||
4. **Leverage Visuals Like a Meme Lord:** Remember, it's video! The screen shows the action, so skip the obvious. "He's running" is snooze-fest; "Dude's sprinting like his pants are on fire!" is gold. Be concise, but punchy—like a viral tweet.
|
||
|
||
{shared_prompt}
|
||
|
||
<Adaptation Process: The Two-Step Vibe Check>
|
||
For each line, follow this fun-first deconstruction and reconstruction:
|
||
|
||
1. **Deconstruct the Literal Translation (Find the Funny):**
|
||
- **Core Vibe Check:** What's the real talk here? What's the laugh angle or relatable hook?
|
||
- **Time-Snack Audit:** Is this word salad way too long for the timing? Hunt for stiff phrases, textbook junk, or literalism bloat. Ask: "Would my grandma say this at a BBQ?"
|
||
- **Naturalness Gut-Check:** Does it sound like a robot wrote it? Note any cringe-worthy formalities.
|
||
|
||
2. **Reconstruct as a {TARGET_LANGUAGE} Dubbing Line (Add the Sass):**
|
||
- **Brevity with a Side of Sass:** Rewrite it short and sweet—aim for half the words, double the charm. Use phrases like "No way!" instead of "That is impossible." Shorter = snappier.
|
||
- **Idioms & Pop Culture FTW:** Drop in everyday {TARGET_LANGUAGE} gems like "That's lit!" or "Bet." If it fits, sneak in a playful nod to memes or shows (e.g., "This is worse than that time in *Stranger Things*!").
|
||
- **Instant Clarity, Zero Boredom:** Audiences hear it once—make it stick like a catchy tune. Start lines with a mic-drop hook: "Hold up—check this!" or "Plot twist: I'm late for tacos."
|
||
- **Match the Vibe (Casual AF):** Keep the source's tone but dial up the fun. Formal? Nah—make it chill. Technical? Simplify with humor. Enthusiastic? Amp it to "OMG, yes!"
|
||
|
||
## INPUT
|
||
<subtitles>
|
||
{lines}
|
||
</subtitles>
|
||
|
||
## Output in only JSON format and no other text
|
||
```json
|
||
{json_format}
|
||
```
|
||
|
||
Note: Start you answer with ```json and end with ```, do not add any other text.
|
||
'''
|
||
|
||
return prompt_expressiveness_v2.strip()
|
||
|
||
|
||
## ================================================================
|
||
# @ step6_splitforsub.py
|
||
def get_align_prompt(src_sub, tr_sub, src_part):
|
||
targ_lang = load_key("target_language")
|
||
src_lang = load_key("whisper.detected_language")
|
||
src_splits = src_part.split('\n')
|
||
num_parts = len(src_splits)
|
||
src_part = src_part.replace('\n', ' [br] ')
|
||
align_parts_json = ','.join(
|
||
f'''
|
||
{{
|
||
"src_part_{i+1}": "{src_splits[i]}",
|
||
"target_part_{i+1}": "Corresponding aligned {targ_lang} subtitle part"
|
||
}}''' for i in range(num_parts)
|
||
)
|
||
|
||
align_prompt = f'''
|
||
## Role
|
||
You are a Netflix subtitle alignment expert fluent in both {src_lang} and {targ_lang}.
|
||
|
||
## Task
|
||
We have {src_lang} and {targ_lang} original subtitles for a Netflix program, as well as a pre-processed split version of {src_lang} subtitles.
|
||
Your task is to create the best splitting scheme for the {targ_lang} subtitles based on this information.
|
||
|
||
1. Analyze the word order and structural correspondence between {src_lang} and {targ_lang} subtitles
|
||
2. Split the {targ_lang} subtitles according to the pre-processed {src_lang} split version
|
||
3. Never leave empty lines. If it's difficult to split based on meaning, you may appropriately rewrite the sentences that need to be aligned
|
||
4. Do not add comments or explanations in the translation, as the subtitles are for the audience to read
|
||
|
||
## INPUT
|
||
<subtitles>
|
||
{src_lang} Original: "{src_sub}"
|
||
{targ_lang} Original: "{tr_sub}"
|
||
Pre-processed {src_lang} Subtitles ([br] indicates split points): {src_part}
|
||
</subtitles>
|
||
|
||
## Output in only JSON format and no other text
|
||
```json
|
||
{{
|
||
"analysis": "Brief analysis of word order, structure, and semantic correspondence between two subtitles",
|
||
"align": [
|
||
{align_parts_json}
|
||
]
|
||
}}
|
||
```
|
||
|
||
Note: Start you answer with ```json and end with ```, do not add any other text.
|
||
'''.strip()
|
||
return align_prompt
|
||
|
||
## ================================================================
|
||
# @ step8_gen_audio_task.py @ step10_gen_audio.py
|
||
def get_subtitle_trim_prompt(text, duration):
|
||
|
||
rule = '''Consider a. Reducing filler words without modifying meaningful content. b. Omitting unnecessary modifiers or pronouns, for example:
|
||
- "Please explain your thought process" can be shortened to "Please explain thought process"
|
||
- "We need to carefully analyze this complex problem" can be shortened to "We need to analyze this problem"
|
||
- "Let's discuss the various different perspectives on this topic" can be shortened to "Let's discuss different perspectives on this topic"
|
||
- "Can you describe in detail your experience from yesterday" can be shortened to "Can you describe yesterday's experience" '''
|
||
|
||
trim_prompt = f'''
|
||
## Role
|
||
You are a professional subtitle editor, editing and optimizing lengthy subtitles that exceed voiceover time before handing them to voice actors.
|
||
Your expertise lies in cleverly shortening subtitles slightly while ensuring the original meaning and structure remain unchanged.
|
||
|
||
## INPUT
|
||
<subtitles>
|
||
Subtitle: "{text}"
|
||
Duration: {duration} seconds
|
||
</subtitles>
|
||
|
||
## Processing Rules
|
||
{rule}
|
||
|
||
## Processing Steps
|
||
Please follow these steps and provide the results in the JSON output:
|
||
1. Analysis: Briefly analyze the subtitle's structure, key information, and filler words that can be omitted.
|
||
2. Trimming: Based on the rules and analysis, optimize the subtitle by making it more concise according to the processing rules.
|
||
|
||
## Output in only JSON format and no other text
|
||
```json
|
||
{{
|
||
"analysis": "Brief analysis of the subtitle, including structure, key information, and potential processing locations",
|
||
"result": "Optimized and shortened subtitle in the original subtitle language"
|
||
}}
|
||
```
|
||
|
||
Note: Start you answer with ```json and end with ```, do not add any other text.
|
||
'''.strip()
|
||
return trim_prompt
|
||
|
||
## ================================================================
|
||
# @ tts_main
|
||
def get_correct_text_prompt(text):
|
||
return f'''
|
||
## Role
|
||
You are a text cleaning expert for TTS (Text-to-Speech) systems.
|
||
|
||
## Task
|
||
Clean the given text by:
|
||
1. Keep only basic punctuation (.,?!)
|
||
2. Preserve the original meaning
|
||
|
||
## INPUT
|
||
{text}
|
||
|
||
## Output in only JSON format and no other text
|
||
```json
|
||
{{
|
||
"text": "cleaned text here"
|
||
}}
|
||
```
|
||
|
||
Note: Start you answer with ```json and end with ```, do not add any other text.
|
||
'''.strip()
|