File size: 22,353 Bytes
dfbb2da 0254d02 dfbb2da |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 |
"""
YouTube Video Summarizer API - Hugging Face Spaces Edition
Flask backend deployed on Hugging Face Spaces.
Provides multilingual YouTube video summarization using:
- Whisper (speech-to-text)
- NLLB-200 (translation)
- Groq API (summarization)
All ML models are FREE and run locally on HF Spaces infrastructure.
"""
from flask import Flask, request, jsonify
from flask_cors import CORS
from dotenv import load_dotenv
import os
import logging
from services.transcript import TranscriptService
from services.summarizer import SummarizerService
from config import (
SUPPORTED_LANGUAGES,
get_language_name,
is_english,
)
# Load environment variables
load_dotenv()
# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
app = Flask(__name__)
# Enable CORS for all origins (allow frontend from any domain)
CORS(app, resources={
r"/*": {
"origins": "*",
"methods": ["GET", "POST", "OPTIONS"],
"allow_headers": ["Content-Type", "Authorization"]
}
})
# Initialize services (lazy-loaded for heavy models)
transcript_service = TranscriptService()
summarizer_service = SummarizerService()
# Translation service is lazy-loaded to avoid loading 2.4GB model on startup
_translation_service = None
def get_translation_service():
"""Lazy-load the translation service."""
global _translation_service
if _translation_service is None:
from services.translation import TranslationService
_translation_service = TranslationService()
return _translation_service
# =============================================================================
# ROOT & HEALTH ENDPOINTS
# =============================================================================
@app.route('/', methods=['GET'])
def root():
"""Root endpoint - serves as health check for HF Spaces"""
return jsonify({
'status': 'healthy',
'service': 'YouTube Summarizer API',
'version': '2.0.0',
'docs': '/api/health for detailed status'
}), 200
@app.route('/api/health', methods=['GET'])
def health_check():
"""Detailed health check endpoint"""
return jsonify({
'status': 'healthy',
'message': 'YouTube Summarizer API is running on Hugging Face Spaces',
'version': '2.0.0',
'features': ['multilingual', 'whisper', 'translation'],
'models': {
'whisper': 'openai/whisper-small',
'translation': 'facebook/nllb-200-distilled-600M',
'summarization': 'groq/llama-3.1-8b-instant'
}
}), 200
@app.route('/api/languages', methods=['GET'])
def get_languages():
"""Get list of supported languages"""
return jsonify({
'success': True,
'languages': SUPPORTED_LANGUAGES
}), 200
@app.route('/api/warmup', methods=['POST'])
def warmup_models():
"""
Pre-load ML models to avoid delay on first request.
This can take 2-5 minutes on first run (downloading models).
"""
try:
results = {}
data = request.get_json() or {}
if data.get('translation', False):
logger.info("Warming up translation model...")
translation_service = get_translation_service()
translation_service.warmup()
results['translation'] = 'loaded'
if data.get('whisper', False):
logger.info("Warming up Whisper model...")
from services.speech_to_text import SpeechToTextService
stt = SpeechToTextService()
stt.warmup()
results['whisper'] = 'loaded'
return jsonify({
'success': True,
'message': 'Models warmed up successfully',
'models': results
}), 200
except Exception as e:
logger.error(f"Warmup failed: {e}")
return jsonify({
'error': 'Warmup failed',
'message': str(e)
}), 500
# =============================================================================
# AUDIO TRANSCRIPTION ENDPOINTS (for Railway integration)
# =============================================================================
@app.route('/api/transcribe-audio', methods=['POST'])
def transcribe_audio():
"""
Transcribe audio using Whisper.
Receives audio as base64 from Railway backend.
"""
try:
data = request.get_json()
if not data or 'audio_base64' not in data:
return jsonify({
'error': 'Missing audio',
'message': 'Please provide audio_base64'
}), 400
import base64
import tempfile
# Decode audio
audio_data = base64.b64decode(data['audio_base64'])
# Save to temp file
with tempfile.NamedTemporaryFile(suffix='.wav', delete=False) as f:
f.write(audio_data)
audio_path = f.name
try:
# Transcribe with Whisper
from services.speech_to_text import SpeechToTextService
stt = SpeechToTextService()
result = stt.transcribe_audio(audio_path)
return jsonify({
'success': True,
'transcript': result['text'],
'language': result['language'],
'word_count': len(result['text'].split())
}), 200
finally:
# Cleanup
import os
if os.path.exists(audio_path):
os.remove(audio_path)
except Exception as e:
logger.error(f"Audio transcription failed: {e}")
return jsonify({
'error': 'Transcription failed',
'message': str(e)
}), 500
@app.route('/api/process-audio', methods=['POST'])
def process_audio():
"""
Full pipeline for audio: Whisper transcription → Translation → Summary.
Receives audio as base64 from Railway backend.
"""
try:
data = request.get_json()
if not data or 'audio_base64' not in data:
return jsonify({
'error': 'Missing audio',
'message': 'Please provide audio_base64'
}), 400
import base64
import tempfile
video_id = data.get('video_id', 'unknown')
summary_type = data.get('summary_type', 'general')
target_language = data.get('target_language', 'eng')
# Decode audio
audio_data = base64.b64decode(data['audio_base64'])
# Save to temp file
with tempfile.NamedTemporaryFile(suffix='.wav', delete=False) as f:
f.write(audio_data)
audio_path = f.name
try:
# Step 1: Transcribe with Whisper
logger.info("Transcribing audio with Whisper...")
from services.speech_to_text import SpeechToTextService
stt = SpeechToTextService()
whisper_result = stt.transcribe_audio(audio_path)
transcript = whisper_result['text']
original_language = whisper_result['language']
original_word_count = len(transcript.split())
logger.info(f"Transcription complete. Language: {original_language}")
# Step 2: Translate to English if needed
english_transcript = transcript
if not is_english(original_language):
logger.info("Translating to English...")
translation_service = get_translation_service()
english_transcript = translation_service.translate_to_english(
transcript,
original_language
)
# Step 3: Summarize
logger.info("Generating summary...")
summary = summarizer_service.summarize(
text=english_transcript,
summary_type=summary_type,
chunk_size=2500,
max_tokens=500
)
# Step 4: Translate summary to target language if needed
final_summary = summary
summary_language = "eng"
if not is_english(target_language):
logger.info(f"Translating summary to {target_language}...")
translation_service = get_translation_service()
final_summary = translation_service.translate_from_english(summary, target_language)
summary_language = target_language
# Calculate statistics
summary_word_count = len(final_summary.split())
compression_ratio = (summary_word_count / original_word_count) * 100 if original_word_count > 0 else 0
response = {
'success': True,
'video_id': video_id,
'original_language': original_language,
'original_language_name': get_language_name(original_language),
'transcript': transcript,
'transcript_source': 'whisper',
'summary': final_summary,
'summary_language': summary_language,
'summary_language_name': get_language_name(summary_language),
'statistics': {
'original_word_count': original_word_count,
'summary_word_count': summary_word_count,
'compression_ratio': round(compression_ratio, 1),
'reading_time_minutes': max(1, summary_word_count // 200)
}
}
if not is_english(original_language):
response['english_transcript'] = english_transcript
if not is_english(target_language):
response['english_summary'] = summary
logger.info("Audio processing complete!")
return jsonify(response), 200
finally:
# Cleanup
import os
if os.path.exists(audio_path):
os.remove(audio_path)
except Exception as e:
logger.error(f"Audio processing failed: {e}")
return jsonify({
'error': 'Processing failed',
'message': str(e)
}), 500
# =============================================================================
# TRANSCRIPT ENDPOINTS
# =============================================================================
@app.route('/api/transcript', methods=['POST'])
def get_transcript():
"""
Extract transcript from YouTube video (multilingual).
Request: { "url": "youtube_url", "use_whisper": true }
Response: { "success": true, "transcript": "...", "language": "tam", ... }
"""
try:
data = request.get_json()
if not data or 'url' not in data:
return jsonify({
'error': 'Missing YouTube URL',
'message': 'Please provide a valid YouTube URL'
}), 400
url = data['url']
use_whisper = data.get('use_whisper', True)
video_id = transcript_service.extract_video_id(url)
result = transcript_service.get_video_transcript(url, use_whisper_fallback=use_whisper)
return jsonify({
'success': True,
'video_id': video_id,
'transcript': result['transcript'],
'language': result['language'],
'language_name': get_language_name(result['language']),
'source': result['source'],
'word_count': result['word_count']
}), 200
except ValueError as e:
return jsonify({'error': 'Invalid URL', 'message': str(e)}), 400
except Exception as e:
logger.error(f"Transcript extraction failed: {e}")
return jsonify({'error': 'Transcript extraction failed', 'message': str(e)}), 500
# =============================================================================
# TRANSLATION ENDPOINTS
# =============================================================================
@app.route('/api/translate', methods=['POST'])
def translate_text():
"""
Translate text between languages.
Request: { "text": "Hello", "source_lang": "eng", "target_lang": "hin" }
Response: { "success": true, "translated_text": "नमस्ते", ... }
"""
try:
data = request.get_json()
if not data or 'text' not in data:
return jsonify({
'error': 'Missing text',
'message': 'Please provide text to translate'
}), 400
text = data['text']
source_lang = data.get('source_lang', 'eng')
target_lang = data.get('target_lang', 'hin')
translation_service = get_translation_service()
translated = translation_service.translate(text, source_lang, target_lang)
return jsonify({
'success': True,
'translated_text': translated,
'source_lang': source_lang,
'source_lang_name': get_language_name(source_lang),
'target_lang': target_lang,
'target_lang_name': get_language_name(target_lang)
}), 200
except ValueError as e:
return jsonify({'error': 'Invalid language', 'message': str(e)}), 400
except Exception as e:
logger.error(f"Translation failed: {e}")
return jsonify({'error': 'Translation failed', 'message': str(e)}), 500
@app.route('/api/detect-language', methods=['POST'])
def detect_language():
"""Detect the language of given text."""
try:
data = request.get_json()
if not data or 'text' not in data:
return jsonify({
'error': 'Missing text',
'message': 'Please provide text for language detection'
}), 400
translation_service = get_translation_service()
result = translation_service.detect_language(data['text'])
return jsonify({
'success': True,
'language': result['code'],
'language_name': result['name']
}), 200
except Exception as e:
logger.error(f"Language detection failed: {e}")
return jsonify({'error': 'Language detection failed', 'message': str(e)}), 500
# =============================================================================
# SUMMARIZATION ENDPOINTS
# =============================================================================
@app.route('/api/summarize', methods=['POST'])
def summarize():
"""
Generate summary from transcript.
Request: { "transcript": "...", "summary_type": "general" }
Response: { "success": true, "summary": "...", "statistics": {...} }
"""
try:
data = request.get_json()
if not data or 'transcript' not in data:
return jsonify({
'error': 'Missing transcript',
'message': 'Please provide transcript text'
}), 400
transcript = data['transcript']
summary_type = data.get('summary_type', 'general')
chunk_size = data.get('chunk_size', 2500)
max_tokens = data.get('max_tokens', 500)
valid_types = ['general', 'detailed', 'bullet_points', 'key_takeaways']
if summary_type not in valid_types:
return jsonify({
'error': 'Invalid summary type',
'message': f'Must be one of: {", ".join(valid_types)}'
}), 400
summary = summarizer_service.summarize(
text=transcript,
summary_type=summary_type,
chunk_size=chunk_size,
max_tokens=max_tokens
)
summary_word_count = len(summary.split())
original_word_count = len(transcript.split())
compression_ratio = (summary_word_count / original_word_count) * 100 if original_word_count > 0 else 0
return jsonify({
'success': True,
'summary': summary,
'statistics': {
'original_word_count': original_word_count,
'summary_word_count': summary_word_count,
'compression_ratio': round(compression_ratio, 1),
'reading_time_minutes': max(1, summary_word_count // 200)
}
}), 200
except Exception as e:
logger.error(f"Summarization failed: {e}")
return jsonify({'error': 'Summarization failed', 'message': str(e)}), 500
# =============================================================================
# FULL PIPELINE ENDPOINT
# =============================================================================
@app.route('/api/process', methods=['POST'])
def process_video():
"""
Full multilingual pipeline: Transcript → Translation → Summary → Translation
Request: {
"url": "youtube_url",
"summary_type": "general",
"target_language": "hin" (optional)
}
"""
try:
data = request.get_json()
if not data or 'url' not in data:
return jsonify({
'error': 'Missing YouTube URL',
'message': 'Please provide a valid YouTube URL'
}), 400
url = data['url']
summary_type = data.get('summary_type', 'general')
target_language = data.get('target_language', 'eng')
chunk_size = data.get('chunk_size', 2500)
max_tokens = data.get('max_tokens', 500)
# Step 1: Extract video ID
video_id = transcript_service.extract_video_id(url)
logger.info(f"Processing video: {video_id}")
# Step 2: Get transcript with language
logger.info("Step 1/4: Extracting transcript...")
transcript_result = transcript_service.get_video_transcript(url, use_whisper_fallback=True)
original_transcript = transcript_result['transcript']
original_language = transcript_result['language']
original_word_count = transcript_result['word_count']
# Step 3: Translate to English if needed
english_transcript = original_transcript
if not is_english(original_language):
logger.info("Step 2/4: Translating to English...")
translation_service = get_translation_service()
english_transcript = translation_service.translate_to_english(
original_transcript,
original_language
)
else:
logger.info("Step 2/4: Skipped (already English)")
# Step 4: Summarize in English
logger.info("Step 3/4: Generating summary...")
summary = summarizer_service.summarize(
text=english_transcript,
summary_type=summary_type,
chunk_size=chunk_size,
max_tokens=max_tokens
)
# Step 5: Translate summary to target language
final_summary = summary
summary_language = "eng"
if not is_english(target_language):
logger.info(f"Step 4/4: Translating summary to {target_language}...")
translation_service = get_translation_service()
final_summary = translation_service.translate_from_english(summary, target_language)
summary_language = target_language
else:
logger.info("Step 4/4: Skipped (English output)")
# Calculate statistics
summary_word_count = len(final_summary.split())
compression_ratio = (summary_word_count / original_word_count) * 100 if original_word_count > 0 else 0
response = {
'success': True,
'video_id': video_id,
'original_language': original_language,
'original_language_name': get_language_name(original_language),
'transcript': original_transcript,
'transcript_source': transcript_result['source'],
'summary': final_summary,
'summary_language': summary_language,
'summary_language_name': get_language_name(summary_language),
'statistics': {
'original_word_count': original_word_count,
'summary_word_count': summary_word_count,
'compression_ratio': round(compression_ratio, 1),
'reading_time_minutes': max(1, summary_word_count // 200)
}
}
if not is_english(original_language):
response['english_transcript'] = english_transcript
if not is_english(target_language):
response['english_summary'] = summary
logger.info("Processing complete!")
return jsonify(response), 200
except ValueError as e:
return jsonify({'error': 'Invalid URL', 'message': str(e)}), 400
except Exception as e:
logger.error(f"Processing failed: {e}")
return jsonify({'error': 'Processing failed', 'message': str(e)}), 500
# =============================================================================
# ERROR HANDLERS
# =============================================================================
@app.errorhandler(404)
def not_found(error):
return jsonify({
'error': 'Not found',
'message': 'The requested endpoint does not exist'
}), 404
@app.errorhandler(500)
def internal_error(error):
return jsonify({
'error': 'Internal server error',
'message': 'An unexpected error occurred'
}), 500
# =============================================================================
# MAIN (for local testing only - gunicorn is used in production)
# =============================================================================
if __name__ == '__main__':
port = int(os.environ.get('PORT', 7860))
if not os.getenv('GROQ_API_KEY'):
print("⚠️ Warning: GROQ_API_KEY not found")
print("Set it in HF Spaces Settings → Secrets")
print("🚀 Starting YouTube Summarizer API...")
print(f"📡 API available at: http://localhost:{port}")
app.run(debug=False, host='0.0.0.0', port=port)
|