karaoke-gen 0.90.1__py3-none-any.whl → 0.96.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (187) hide show
  1. backend/.coveragerc +20 -0
  2. backend/.gitignore +37 -0
  3. backend/Dockerfile +43 -0
  4. backend/Dockerfile.base +74 -0
  5. backend/README.md +242 -0
  6. backend/__init__.py +0 -0
  7. backend/api/__init__.py +0 -0
  8. backend/api/dependencies.py +457 -0
  9. backend/api/routes/__init__.py +0 -0
  10. backend/api/routes/admin.py +742 -0
  11. backend/api/routes/audio_search.py +903 -0
  12. backend/api/routes/auth.py +348 -0
  13. backend/api/routes/file_upload.py +2076 -0
  14. backend/api/routes/health.py +344 -0
  15. backend/api/routes/internal.py +435 -0
  16. backend/api/routes/jobs.py +1610 -0
  17. backend/api/routes/review.py +652 -0
  18. backend/api/routes/themes.py +162 -0
  19. backend/api/routes/users.py +1014 -0
  20. backend/config.py +172 -0
  21. backend/main.py +133 -0
  22. backend/middleware/__init__.py +5 -0
  23. backend/middleware/audit_logging.py +124 -0
  24. backend/models/__init__.py +0 -0
  25. backend/models/job.py +519 -0
  26. backend/models/requests.py +123 -0
  27. backend/models/theme.py +153 -0
  28. backend/models/user.py +254 -0
  29. backend/models/worker_log.py +164 -0
  30. backend/pyproject.toml +29 -0
  31. backend/quick-check.sh +93 -0
  32. backend/requirements.txt +29 -0
  33. backend/run_tests.sh +60 -0
  34. backend/services/__init__.py +0 -0
  35. backend/services/audio_analysis_service.py +243 -0
  36. backend/services/audio_editing_service.py +278 -0
  37. backend/services/audio_search_service.py +702 -0
  38. backend/services/auth_service.py +630 -0
  39. backend/services/credential_manager.py +792 -0
  40. backend/services/discord_service.py +172 -0
  41. backend/services/dropbox_service.py +301 -0
  42. backend/services/email_service.py +1093 -0
  43. backend/services/encoding_interface.py +454 -0
  44. backend/services/encoding_service.py +405 -0
  45. backend/services/firestore_service.py +512 -0
  46. backend/services/flacfetch_client.py +573 -0
  47. backend/services/gce_encoding/README.md +72 -0
  48. backend/services/gce_encoding/__init__.py +22 -0
  49. backend/services/gce_encoding/main.py +589 -0
  50. backend/services/gce_encoding/requirements.txt +16 -0
  51. backend/services/gdrive_service.py +356 -0
  52. backend/services/job_logging.py +258 -0
  53. backend/services/job_manager.py +842 -0
  54. backend/services/job_notification_service.py +271 -0
  55. backend/services/local_encoding_service.py +590 -0
  56. backend/services/local_preview_encoding_service.py +407 -0
  57. backend/services/lyrics_cache_service.py +216 -0
  58. backend/services/metrics.py +413 -0
  59. backend/services/packaging_service.py +287 -0
  60. backend/services/rclone_service.py +106 -0
  61. backend/services/storage_service.py +209 -0
  62. backend/services/stripe_service.py +275 -0
  63. backend/services/structured_logging.py +254 -0
  64. backend/services/template_service.py +330 -0
  65. backend/services/theme_service.py +469 -0
  66. backend/services/tracing.py +543 -0
  67. backend/services/user_service.py +721 -0
  68. backend/services/worker_service.py +558 -0
  69. backend/services/youtube_service.py +112 -0
  70. backend/services/youtube_upload_service.py +445 -0
  71. backend/tests/__init__.py +4 -0
  72. backend/tests/conftest.py +224 -0
  73. backend/tests/emulator/__init__.py +7 -0
  74. backend/tests/emulator/conftest.py +88 -0
  75. backend/tests/emulator/test_e2e_cli_backend.py +1053 -0
  76. backend/tests/emulator/test_emulator_integration.py +356 -0
  77. backend/tests/emulator/test_style_loading_direct.py +436 -0
  78. backend/tests/emulator/test_worker_logs_direct.py +229 -0
  79. backend/tests/emulator/test_worker_logs_subcollection.py +443 -0
  80. backend/tests/requirements-test.txt +10 -0
  81. backend/tests/requirements.txt +6 -0
  82. backend/tests/test_admin_email_endpoints.py +411 -0
  83. backend/tests/test_api_integration.py +460 -0
  84. backend/tests/test_api_routes.py +93 -0
  85. backend/tests/test_audio_analysis_service.py +294 -0
  86. backend/tests/test_audio_editing_service.py +386 -0
  87. backend/tests/test_audio_search.py +1398 -0
  88. backend/tests/test_audio_services.py +378 -0
  89. backend/tests/test_auth_firestore.py +231 -0
  90. backend/tests/test_config_extended.py +68 -0
  91. backend/tests/test_credential_manager.py +377 -0
  92. backend/tests/test_dependencies.py +54 -0
  93. backend/tests/test_discord_service.py +244 -0
  94. backend/tests/test_distribution_services.py +820 -0
  95. backend/tests/test_dropbox_service.py +472 -0
  96. backend/tests/test_email_service.py +492 -0
  97. backend/tests/test_emulator_integration.py +322 -0
  98. backend/tests/test_encoding_interface.py +412 -0
  99. backend/tests/test_file_upload.py +1739 -0
  100. backend/tests/test_flacfetch_client.py +632 -0
  101. backend/tests/test_gdrive_service.py +524 -0
  102. backend/tests/test_instrumental_api.py +431 -0
  103. backend/tests/test_internal_api.py +343 -0
  104. backend/tests/test_job_creation_regression.py +583 -0
  105. backend/tests/test_job_manager.py +339 -0
  106. backend/tests/test_job_manager_notifications.py +329 -0
  107. backend/tests/test_job_notification_service.py +443 -0
  108. backend/tests/test_jobs_api.py +273 -0
  109. backend/tests/test_local_encoding_service.py +423 -0
  110. backend/tests/test_local_preview_encoding_service.py +567 -0
  111. backend/tests/test_main.py +87 -0
  112. backend/tests/test_models.py +918 -0
  113. backend/tests/test_packaging_service.py +382 -0
  114. backend/tests/test_requests.py +201 -0
  115. backend/tests/test_routes_jobs.py +282 -0
  116. backend/tests/test_routes_review.py +337 -0
  117. backend/tests/test_services.py +556 -0
  118. backend/tests/test_services_extended.py +112 -0
  119. backend/tests/test_storage_service.py +448 -0
  120. backend/tests/test_style_upload.py +261 -0
  121. backend/tests/test_template_service.py +295 -0
  122. backend/tests/test_theme_service.py +516 -0
  123. backend/tests/test_unicode_sanitization.py +522 -0
  124. backend/tests/test_upload_api.py +256 -0
  125. backend/tests/test_validate.py +156 -0
  126. backend/tests/test_video_worker_orchestrator.py +847 -0
  127. backend/tests/test_worker_log_subcollection.py +509 -0
  128. backend/tests/test_worker_logging.py +365 -0
  129. backend/tests/test_workers.py +1116 -0
  130. backend/tests/test_workers_extended.py +178 -0
  131. backend/tests/test_youtube_service.py +247 -0
  132. backend/tests/test_youtube_upload_service.py +568 -0
  133. backend/validate.py +173 -0
  134. backend/version.py +27 -0
  135. backend/workers/README.md +597 -0
  136. backend/workers/__init__.py +11 -0
  137. backend/workers/audio_worker.py +618 -0
  138. backend/workers/lyrics_worker.py +683 -0
  139. backend/workers/render_video_worker.py +483 -0
  140. backend/workers/screens_worker.py +525 -0
  141. backend/workers/style_helper.py +198 -0
  142. backend/workers/video_worker.py +1277 -0
  143. backend/workers/video_worker_orchestrator.py +701 -0
  144. backend/workers/worker_logging.py +278 -0
  145. karaoke_gen/instrumental_review/static/index.html +7 -4
  146. karaoke_gen/karaoke_finalise/karaoke_finalise.py +6 -1
  147. karaoke_gen/utils/__init__.py +163 -8
  148. karaoke_gen/video_background_processor.py +9 -4
  149. {karaoke_gen-0.90.1.dist-info → karaoke_gen-0.96.0.dist-info}/METADATA +1 -1
  150. {karaoke_gen-0.90.1.dist-info → karaoke_gen-0.96.0.dist-info}/RECORD +186 -41
  151. lyrics_transcriber/correction/agentic/providers/config.py +9 -5
  152. lyrics_transcriber/correction/agentic/providers/langchain_bridge.py +1 -51
  153. lyrics_transcriber/correction/corrector.py +192 -130
  154. lyrics_transcriber/correction/operations.py +24 -9
  155. lyrics_transcriber/frontend/package-lock.json +2 -2
  156. lyrics_transcriber/frontend/package.json +1 -1
  157. lyrics_transcriber/frontend/src/components/AIFeedbackModal.tsx +1 -1
  158. lyrics_transcriber/frontend/src/components/CorrectedWordWithActions.tsx +11 -7
  159. lyrics_transcriber/frontend/src/components/EditActionBar.tsx +31 -5
  160. lyrics_transcriber/frontend/src/components/EditModal.tsx +28 -10
  161. lyrics_transcriber/frontend/src/components/EditTimelineSection.tsx +123 -27
  162. lyrics_transcriber/frontend/src/components/EditWordList.tsx +112 -60
  163. lyrics_transcriber/frontend/src/components/Header.tsx +90 -76
  164. lyrics_transcriber/frontend/src/components/LyricsAnalyzer.tsx +53 -31
  165. lyrics_transcriber/frontend/src/components/LyricsSynchronizer/SyncControls.tsx +44 -13
  166. lyrics_transcriber/frontend/src/components/LyricsSynchronizer/TimelineCanvas.tsx +66 -50
  167. lyrics_transcriber/frontend/src/components/LyricsSynchronizer/index.tsx +124 -30
  168. lyrics_transcriber/frontend/src/components/ReferenceView.tsx +1 -1
  169. lyrics_transcriber/frontend/src/components/TimelineEditor.tsx +12 -5
  170. lyrics_transcriber/frontend/src/components/TimingOffsetModal.tsx +3 -3
  171. lyrics_transcriber/frontend/src/components/TranscriptionView.tsx +1 -1
  172. lyrics_transcriber/frontend/src/components/WordDivider.tsx +11 -7
  173. lyrics_transcriber/frontend/src/components/shared/components/Word.tsx +4 -2
  174. lyrics_transcriber/frontend/src/hooks/useManualSync.ts +103 -1
  175. lyrics_transcriber/frontend/src/theme.ts +42 -15
  176. lyrics_transcriber/frontend/tsconfig.tsbuildinfo +1 -1
  177. lyrics_transcriber/frontend/vite.config.js +5 -0
  178. lyrics_transcriber/frontend/web_assets/assets/{index-BECn1o8Q.js → index-BSMgOq4Z.js} +6959 -5782
  179. lyrics_transcriber/frontend/web_assets/assets/index-BSMgOq4Z.js.map +1 -0
  180. lyrics_transcriber/frontend/web_assets/index.html +6 -2
  181. lyrics_transcriber/frontend/web_assets/nomad-karaoke-logo.svg +5 -0
  182. lyrics_transcriber/output/generator.py +17 -3
  183. lyrics_transcriber/output/video.py +60 -95
  184. lyrics_transcriber/frontend/web_assets/assets/index-BECn1o8Q.js.map +0 -1
  185. {karaoke_gen-0.90.1.dist-info → karaoke_gen-0.96.0.dist-info}/WHEEL +0 -0
  186. {karaoke_gen-0.90.1.dist-info → karaoke_gen-0.96.0.dist-info}/entry_points.txt +0 -0
  187. {karaoke_gen-0.90.1.dist-info → karaoke_gen-0.96.0.dist-info}/licenses/LICENSE +0 -0
lyrics_transcriber/frontend/web_assets/index.html CHANGED
@@ -2,6 +2,10 @@
2
2
  <html lang="en">
3
3
  <head>
4
4
  <meta charset="UTF-8" />
5
+ <!-- Load Inter font to match karaoke-gen styling -->
6
+ <link rel="preconnect" href="https://fonts.googleapis.com">
7
+ <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
8
+ <link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&display=swap" rel="stylesheet">
5
9
  <link rel="icon" type="image/x-icon" href="/favicon.ico" />
6
10
  <link rel="icon" type="image/png" sizes="16x16" href="/favicon-16x16.png" />
7
11
  <link rel="icon" type="image/png" sizes="32x32" href="/favicon-32x32.png" />
@@ -9,8 +13,8 @@
9
13
  <link rel="icon" type="image/png" sizes="192x192" href="/android-chrome-192x192.png" />
10
14
  <link rel="icon" type="image/png" sizes="512x512" href="/android-chrome-512x512.png" />
11
15
  <meta name="viewport" content="width=device-width, initial-scale=1.0" />
12
- <title>Nomad Karaoke: Lyrics Review</title>
13
- <script type="module" crossorigin src="/assets/index-BECn1o8Q.js"></script>
16
+ <title>Nomad Karaoke: Lyrics Transcription Review</title>
17
+ <script type="module" crossorigin src="/assets/index-BSMgOq4Z.js"></script>
14
18
  </head>
15
19
  <body>
16
20
  <div id="root"></div>
lyrics_transcriber/frontend/web_assets/nomad-karaoke-logo.svg ADDED
@@ -0,0 +1,5 @@
1
+ <?xml version="1.0" encoding="UTF-8" standalone="no"?>
2
+ <!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
3
+ <svg xmlns="http://www.w3.org/2000/svg" version="1.1" viewBox="45 60 255 135">
4
+ <g data-v-70b83f88="" fill="#ff7acc" class="basesvg" transform="translate(48.368003845214844,62.62239074707031)"><g fill-rule="" class="tp-name" transform="translate(0,0)"><g transform="scale(1.4000000000000004)"><g stroke="#ff7acc" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" paint-order="stroke" data-gra-attr="stroke" fill-opacity="0"><path d="M1.4-33.44L1.4 0C31.48 0 3.96 0 34.04 0L34.04-32.64 17.81-32.64 17.81-20.61 1.4-33.44ZM52.21-33.76C42.6-33.76 34.81-25.97 34.81-16.37 34.81-6.76 42.6 1.03 52.21 1.03 61.81 1.03 69.6-6.76 69.6-16.37 69.6-25.97 61.81-33.76 52.21-33.76ZM70.7 0L103.34 0 103.25-33.9 86.93-21.54 70.61-33.9 70.7 0ZM102.34 0C138.2 0 107.52 0 143.56 0L122.95-34.93 102.34 0ZM158.84 0.05C167.84 0.05 175.16-7.27 175.16-16.27 175.16-25.27 167.84-32.64 158.84-32.64L142.52-32.64C142.52 0.75 142.52-33.34 142.52 0.05L158.84 0.05Z" transform="translate(-1.399999976158142, 34.93000030517578)"></path></g><g transform="translate(0,38.959999084472656)"><g stroke="#ff7acc" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" paint-order="stroke" data-gra-attr="stroke" fill="#ff7acc" fill-opacity="0" transform="scale(1.02719)"><path d="M24.43 0L17.67 0 7.98-11.87 7.98 0 2.63 0 2.63-26.64 7.98-26.64 7.98-14.69 17.67-26.64 24.12-26.64 13.13-13.44 24.43 0ZM45.03 0L43.27-5.08 32.66-5.08 30.91 0 25.3 0 34.88-26.68 41.1-26.68 50.68 0 45.03 0ZM34.11-9.35L41.82-9.35 37.97-20.5 34.11-9.35ZM73.19 0L67.01 0 61.13-10.38 58.61-10.38 58.61 0 53.27 0 53.27-26.64 63.27-26.64Q66.36-26.64 68.53-25.55 70.71-24.47 71.8-22.61 72.89-20.76 72.89-18.47L72.89-18.47Q72.89-15.84 71.36-13.72 69.83-11.6 66.82-10.8L66.82-10.8 73.19 0ZM58.61-22.21L58.61-14.39 63.08-14.39Q65.25-14.39 66.32-15.44 67.39-16.49 67.39-18.36L67.39-18.36Q67.39-20.19 66.32-21.2 65.25-22.21 63.08-22.21L63.08-22.21 58.61-22.21ZM94.82 0L93.07-5.08 82.46-5.08 80.7 0 75.09 0 84.67-26.68 90.89-26.68 100.47 0 94.82 0ZM83.91-9.35L91.62-9.35 87.76-20.5 83.91-9.35ZM115.43 0.27Q111.69 0.27 108.56-1.49 105.43-3.24 103.6-6.35 101.76-9.47 101.76-13.4L101.76-13.4Q101.76-17.29 103.6-20.4 105.43-23.51 108.56-25.27 111.69-27.02 115.43-27.02L115.43-27.02Q119.21-27.02 122.32-25.27 125.43-23.51 127.24-20.4 129.05-17.29 129.05-13.4L129.05-13.4Q129.05-9.47 127.24-6.35 125.43-3.24 122.3-1.49 119.17 0.27 115.43 0.27L115.43 0.27ZM115.43-4.5Q117.83-4.5 119.66-5.59 121.5-6.68 122.53-8.7 123.56-10.73 123.56-13.4L123.56-13.4Q123.56-16.07 122.53-18.07 121.5-20.08 119.66-21.15 117.83-22.21 115.43-22.21L115.43-22.21Q113.02-22.21 111.17-21.15 109.32-20.08 108.29-18.07 107.26-16.07 107.26-13.4L107.26-13.4Q107.26-10.73 108.29-8.7 109.32-6.68 111.17-5.59 113.02-4.5 115.43-4.5L115.43-4.5ZM153.82 0L147.06 0 137.37-11.87 137.37 0 132.02 0 132.02-26.64 137.37-26.64 137.37-14.69 147.06-26.64 153.51-26.64 142.52-13.44 153.82 0ZM171.79-22.33L161.67-22.33 161.67-15.65 170.64-15.65 170.64-11.41 161.67-11.41 161.67-4.35 171.79-4.35 171.79 0 156.33 0 156.33-26.68 171.79-26.68 171.79-22.33Z" transform="translate(-2.630000114440918, 27.020000457763672)"></path></g></g></g></g> <g data-gra="path-slogan" fill-rule="" class="tp-slogan" fill="#ffdf6b" transform="translate(5,111.788818359375)"><rect x="0" height="1" y="5.9832000732421875" width="14.278396606445312"></rect> <rect height="1" y="5.9832000732421875" width="14.278396606445312" x="218.985595703125"></rect> <g transform="translate(17.278396606445312,0)"><g transform="scale(1.2800000000000002)"><path d="M10.21-8.38L12.02-8.38L9.68 0L7.70 0L6.13-5.96L4.49 0L2.52 0.01L0.26-8.38L2.06-8.38L3.54-1.87L5.24-8.38L7.12-8.38L8.72-1.91L10.21-8.38ZM18.38-8.38L20.06-8.38L20.06 0L18.38 0L18.38-3.56L14.80-3.56L14.80 0L13.12 0L13.12-8.38L14.80-8.38L14.80-4.93L18.38-4.93L18.38-8.38ZM26.58-7.02L23.40-7.02L23.40-4.92L26.22-4.92L26.22-3.59L23.40-3.59L23.40-1.37L26.58-1.37L26.58 0L21.72 0L21.72-8.39L26.58-8.39L26.58-7.02ZM34.37 0L32.42 0L30.58-3.26L29.78-3.26L29.78 0L28.10 0L28.10-8.38L31.25-8.38Q32.22-8.38 32.90-8.03Q33.59-7.69 33.93-7.11Q34.27-6.53 34.27-5.81L34.27-5.81Q34.27-4.98 33.79-4.31Q33.31-3.65 32.36-3.40L32.36-3.40L34.37 0ZM29.78-6.98L29.78-4.52L31.19-4.52Q31.87-4.52 32.21-4.85Q32.54-5.18 32.54-5.77L32.54-5.77Q32.54-6.35 32.21-6.67Q31.87-6.98 31.19-6.98L31.19-6.98L29.78-6.98ZM40.66-7.02L37.48-7.02L37.48-4.92L40.30-4.92L40.30-3.59L37.48-3.59L37.48-1.37L40.66-1.37L40.66 0L35.80 0L35.80-8.39L40.66-8.39L40.66-7.02ZM47.92-8.38L49.70-8.38L46.63 0L44.59 0L41.52-8.38L43.32-8.38L45.62-1.72L47.92-8.38ZM55.57-7.02L52.39-7.02L52.39-4.92L55.21-4.92L55.21-3.59L52.39-3.59L52.39-1.37L55.57-1.37L55.57 0L50.71 0L50.71-8.39L55.57-8.39L55.57-7.02ZM63.36 0L61.42 0L59.57-3.26L58.78-3.26L58.78 0L57.10 0L57.10-8.38L60.24-8.38Q61.21-8.38 61.90-8.03Q62.58-7.69 62.92-7.11Q63.26-6.53 63.26-5.81L63.26-5.81Q63.26-4.98 62.78-4.31Q62.30-3.65 61.36-3.40L61.36-3.40L63.36 0ZM58.78-6.98L58.78-4.52L60.18-4.52Q60.86-4.52 61.20-4.85Q61.54-5.18 61.54-5.77L61.54-5.77Q61.54-6.35 61.20-6.67Q60.86-6.98 60.18-6.98L60.18-6.98L58.78-6.98ZM72.43-8.38L74.30-8.38L71.47-2.92L71.47 0L69.79 0L69.79-2.92L66.95-8.38L68.84-8.38L70.64-4.55L72.43-8.38ZM79.16 0.08Q77.99 0.08 77.00-0.47Q76.02-1.02 75.44-2.00Q74.87-2.98 74.87-4.21L74.87-4.21Q74.87-5.44 75.44-6.41Q76.02-7.39 77.00-7.94Q77.99-8.50 79.16-8.50L79.16-8.50Q80.35-8.50 81.33-7.94Q82.31-7.39 82.88-6.41Q83.45-5.44 83.45-4.21L83.45-4.21Q83.45-2.98 82.88-2.00Q82.31-1.02 81.32-0.47Q80.34 0.08 79.16 0.08L79.16 0.08ZM79.16-1.42Q79.92-1.42 80.50-1.76Q81.07-2.10 81.40-2.74Q81.72-3.37 81.72-4.21L81.72-4.21Q81.72-5.05 81.40-5.68Q81.07-6.31 80.50-6.65Q79.92-6.98 79.16-6.98L79.16-6.98Q78.41-6.98 77.83-6.65Q77.24-6.31 76.92-5.68Q76.60-5.05 76.60-4.21L76.60-4.21Q76.60-3.37 76.92-2.74Q77.24-2.10 77.83-1.76Q78.41-1.42 79.16-1.42L79.16-1.42ZM84.67-8.38L86.35-8.38L86.35-3.19Q86.35-2.34 86.80-1.89Q87.24-1.44 88.04-1.44L88.04-1.44Q88.86-1.44 89.30-1.89Q89.75-2.34 89.75-3.19L89.75-3.19L89.75-8.38L91.44-8.38L91.44-3.20Q91.44-2.14 90.98-1.40Q90.52-0.66 89.74-0.29Q88.97 0.08 88.02 0.08L88.02 0.08Q87.08 0.08 86.32-0.29Q85.56-0.66 85.12-1.40Q84.67-2.14 84.67-3.20L84.67-3.20L84.67-8.38ZM101.60 0L101.05-1.60L97.72-1.60L97.16 0L95.40 0L98.41-8.39L100.37-8.39L103.38 0L101.60 0ZM98.17-2.94L100.60-2.94L99.38-6.44L98.17-2.94ZM110.77 0L108.83 0L106.98-3.26L106.19-3.26L106.19 0L104.51 0L104.51-8.38L107.65-8.38Q108.62-8.38 109.31-8.03Q109.99-7.69 110.33-7.11Q110.68-6.53 110.68-5.81L110.68-5.81Q110.68-4.98 110.20-4.31Q109.72-3.65 108.77-3.40L108.77-3.40L110.77 0ZM106.19-6.98L106.19-4.52L107.59-4.52Q108.28-4.52 108.61-4.85Q108.95-5.18 108.95-5.77L108.95-5.77Q108.95-6.35 108.61-6.67Q108.28-6.98 107.59-6.98L107.59-6.98L106.19-6.98ZM117.06-7.02L113.88-7.02L113.88-4.92L116.70-4.92L116.70-3.59L113.88-3.59L113.88-1.37L117.06-1.37L117.06 0L112.20 0L112.20-8.39L117.06-8.39L117.06-7.02ZM118.72-1.76L120.42-1.76L119.02 1.61L117.94 1.61L118.72-1.76ZM127.38 0.08Q126.50 0.08 125.80-0.22Q125.10-0.52 124.69-1.08Q124.28-1.64 124.27-2.41L124.27-2.41L126.07-2.41Q126.11-1.90 126.44-1.60Q126.77-1.30 127.34-1.30L127.34-1.30Q127.93-1.30 128.27-1.58Q128.60-1.86 128.60-2.32L128.60-2.32Q128.60-2.69 128.38-2.93Q128.15-3.17 127.81-3.31Q127.46-3.44 126.86-3.61L126.86-3.61Q126.05-3.85 125.54-4.09Q125.03-4.32 124.66-4.79Q124.30-5.27 124.30-6.06L124.30-6.06Q124.30-6.80 124.67-7.36Q125.04-7.91 125.71-8.20Q126.38-8.50 127.25-8.50L127.25-8.50Q128.54-8.50 129.35-7.87Q130.16-7.24 130.25-6.11L130.25-6.11L128.40-6.11Q128.38-6.54 128.03-6.82Q127.69-7.10 127.13-7.10L127.13-7.10Q126.64-7.10 126.34-6.85Q126.05-6.60 126.05-6.12L126.05-6.12Q126.05-5.78 126.27-5.56Q126.49-5.34 126.82-5.20Q127.15-5.06 127.75-4.88L127.75-4.88Q128.57-4.64 129.08-4.40Q129.60-4.16 129.97-3.68Q130.34-3.20 130.34-2.42L130.34-2.42Q130.34-1.75 130.00-1.18Q129.65-0.60 128.98-0.26Q128.30 0.08 127.38 0.08L127.38 0.08ZM131.80-8.38L133.48-8.38L133.48 0L131.80 0L131.80-8.38ZM142.30-8.39L142.30 0L140.62 0L136.81-5.75L136.81 0L135.13 0L135.13-8.39L136.81-8.39L140.62-2.63L140.62-8.39L142.30-8.39ZM151.72-5.86L149.78-5.86Q149.50-6.38 148.99-6.66Q148.49-6.94 147.82-6.94L147.82-6.94Q147.07-6.94 146.50-6.60Q145.92-6.26 145.60-5.64Q145.27-5.02 145.27-4.20L145.27-4.20Q145.27-3.36 145.60-2.74Q145.93-2.11 146.52-1.78Q147.11-1.44 147.89-1.44L147.89-1.44Q148.85-1.44 149.46-1.95Q150.07-2.46 150.26-3.37L150.26-3.37L147.38-3.37L147.38-4.66L151.92-4.66L151.92-3.19Q151.75-2.32 151.20-1.57Q150.65-0.83 149.78-0.38Q148.91 0.07 147.83 0.07L147.83 0.07Q146.62 0.07 145.64-0.47Q144.66-1.02 144.10-1.99Q143.54-2.96 143.54-4.20L143.54-4.20Q143.54-5.44 144.10-6.41Q144.66-7.39 145.64-7.94Q146.62-8.48 147.82-8.48L147.82-8.48Q149.23-8.48 150.28-7.79Q151.32-7.10 151.72-5.86L151.72-5.86ZM153.53-8.52L155.34-8.52L155.15-2.72L153.73-2.72L153.53-8.52ZM154.48 0.08Q154.02 0.08 153.73-0.20Q153.43-0.48 153.43-0.90L153.43-0.90Q153.43-1.32 153.73-1.60Q154.02-1.88 154.48-1.88L154.48-1.88Q154.92-1.88 155.21-1.60Q155.50-1.32 155.50-0.90L155.50-0.90Q155.50-0.48 155.21-0.20Q154.92 0.08 154.48 0.08L154.48 0.08Z" transform="translate(-0.264, 8.52)"></path></g></g></g></g>
5
+ </svg>
lyrics_transcriber/output/generator.py CHANGED
@@ -148,8 +148,21 @@ class OutputGenerator:
148
148
  audio_filepath: str,
149
149
  artist: Optional[str] = None,
150
150
  title: Optional[str] = None,
151
+ ass_only: bool = False,
151
152
  ) -> OutputPaths:
152
- """Generate all requested output formats."""
153
+ """Generate all requested output formats.
154
+
155
+ Args:
156
+ transcription_corrected: Corrected transcription data
157
+ lyrics_results: Lyrics data from various providers
158
+ output_prefix: Prefix for output filenames
159
+ audio_filepath: Path to audio file
160
+ artist: Optional artist name
161
+ title: Optional title
162
+ ass_only: If True (only in preview_mode), generate only ASS subtitles
163
+ without video encoding. Useful when video encoding is offloaded
164
+ to an external service.
165
+ """
153
166
  outputs = OutputPaths()
154
167
 
155
168
  try:
@@ -165,8 +178,9 @@ class OutputGenerator:
165
178
  # Generate ASS subtitles for preview
166
179
  outputs.ass = self.subtitle.generate_ass(transcription_corrected.resized_segments, output_prefix, audio_filepath)
167
180
 
168
- # Generate preview video
169
- outputs.video = self.video.generate_preview_video(outputs.ass, audio_filepath, output_prefix)
181
+ # Generate preview video (unless ass_only mode for GCE encoding)
182
+ if not ass_only:
183
+ outputs.video = self.video.generate_preview_video(outputs.ass, audio_filepath, output_prefix)
170
184
 
171
185
  return outputs
172
186
 
lyrics_transcriber/output/video.py CHANGED
@@ -249,6 +249,9 @@ class VideoGenerator:
249
249
  def generate_preview_video(self, ass_path: str, audio_path: str, output_prefix: str) -> str:
250
250
  """Generate lower resolution MP4 preview video with lyrics overlay.
251
251
 
252
+ Delegates to LocalPreviewEncodingService for the actual encoding to ensure
253
+ consistent preview generation across local CLI, Cloud Run, and GCE worker.
254
+
252
255
  Args:
253
256
  ass_path: Path to ASS subtitles file
254
257
  audio_path: Path to audio file
@@ -257,6 +260,11 @@ class VideoGenerator:
257
260
  Returns:
258
261
  Path to generated preview video file
259
262
  """
263
+ from backend.services.local_preview_encoding_service import (
264
+ LocalPreviewEncodingService,
265
+ PreviewEncodingConfig,
266
+ )
267
+
260
268
  self.logger.info("Generating preview video with lyrics overlay")
261
269
  output_path = os.path.join(self.cache_dir, f"{output_prefix}_preview.mp4")
262
270
 
@@ -269,17 +277,36 @@ class VideoGenerator:
269
277
  try:
270
278
  # Create a temporary copy of the ASS file with a unique filename
271
279
  import time
280
+ import shutil
272
281
 
273
282
  safe_prefix = "".join(c if c.isalnum() else "_" for c in output_prefix)
274
283
  timestamp = int(time.time() * 1000)
275
284
  temp_ass_path = os.path.join(self.cache_dir, f"temp_preview_subtitles_{safe_prefix}_{timestamp}.ass")
276
- import shutil
277
285
 
278
286
  shutil.copy2(ass_path, temp_ass_path)
279
287
  self.logger.debug(f"Created temporary ASS file: {temp_ass_path}")
280
288
 
281
- cmd = self._build_preview_ffmpeg_command(temp_ass_path, audio_path, output_path)
282
- self._run_ffmpeg_command(cmd)
289
+ # Get font path from styles configuration
290
+ karaoke_styles = self.styles.get("karaoke", {})
291
+ font_path = karaoke_styles.get("font_path")
292
+
293
+ # Build config for LocalPreviewEncodingService
294
+ config = PreviewEncodingConfig(
295
+ ass_path=temp_ass_path,
296
+ audio_path=audio_path,
297
+ output_path=output_path,
298
+ background_image_path=self.background_image,
299
+ background_color=self.background_color,
300
+ font_path=font_path if font_path and os.path.isfile(font_path) else None,
301
+ )
302
+
303
+ # Use LocalPreviewEncodingService for consistent encoding
304
+ service = LocalPreviewEncodingService(logger=self.logger)
305
+ result = service.encode_preview(config)
306
+
307
+ if not result.success:
308
+ raise RuntimeError(f"Preview encoding failed: {result.error}")
309
+
283
310
  self.logger.info(f"Preview video generated: {output_path}")
284
311
 
285
312
  # Clean up temporary file
@@ -352,19 +379,44 @@ class VideoGenerator:
352
379
  self.logger.error(f"Failed to resize background image: {e.output}")
353
380
  raise
354
381
 
382
+ def _escape_ffmpeg_filter_path(self, path: str) -> str:
383
+ """Escape a path for FFmpeg filter expressions (for subprocess without shell).
384
+
385
+ When using subprocess with a command list (no shell), FFmpeg receives the
386
+ filter string directly. FFmpeg's filter parser requires escaping:
387
+ - Backslashes: double them (\ -> \\)
388
+ - Single quotes/apostrophes: escape with three backslashes (' -> \\')
389
+ - Spaces: escape with backslash ( -> \ )
390
+
391
+ Note: This is different from shell escaping. The '\\'\\''' pattern used for
392
+ shell escaping does NOT work when subprocess passes args directly to FFmpeg.
393
+
394
+ Example: "I'm With You" becomes "I\\\\'m\\ With\\ You"
395
+ """
396
+ # First escape existing backslashes (\ -> \\)
397
+ escaped = path.replace("\\", "\\\\")
398
+ # Escape single quotes (' -> \\')
399
+ # In the actual string we need 3 backslashes before the quote
400
+ escaped = escaped.replace("'", "\\\\\\'")
401
+ # Escape spaces
402
+ escaped = escaped.replace(" ", "\\ ")
403
+ return escaped
404
+
355
405
  def _build_ass_filter(self, ass_path: str) -> str:
356
406
  """Build ASS filter with font directory support."""
357
- ass_filter = f"ass={ass_path}"
358
-
407
+ escaped_ass_path = self._escape_ffmpeg_filter_path(ass_path)
408
+ ass_filter = f"ass={escaped_ass_path}"
409
+
359
410
  # Get font path from styles configuration
360
411
  karaoke_styles = self.styles.get("karaoke", {})
361
412
  font_path = karaoke_styles.get("font_path")
362
-
413
+
363
414
  if font_path and os.path.isfile(font_path):
364
415
  font_dir = os.path.dirname(font_path)
365
- ass_filter += f":fontsdir={font_dir}"
416
+ escaped_font_dir = self._escape_ffmpeg_filter_path(font_dir)
417
+ ass_filter += f":fontsdir={escaped_font_dir}"
366
418
  self.logger.info(f"Returning ASS filter with fonts dir: {ass_filter}")
367
-
419
+
368
420
  return ass_filter
369
421
 
370
422
  def _build_ffmpeg_command(self, ass_path: str, audio_path: str, output_path: str) -> List[str]:
@@ -439,93 +491,6 @@ class VideoGenerator:
439
491
 
440
492
  return cmd
441
493
 
442
- def _build_preview_ffmpeg_command(self, ass_path: str, audio_path: str, output_path: str) -> List[str]:
443
- """Build FFmpeg command for preview video generation with hardware acceleration when available."""
444
- # Use even lower resolution for preview (480x270 instead of 640x360 for faster encoding)
445
- width, height = 480, 270
446
-
447
- cmd = [
448
- "ffmpeg",
449
- "-hide_banner",
450
- "-loglevel", "error",
451
- "-r", "24", # Reduced frame rate to 24 fps for faster encoding
452
- ]
453
-
454
- # Add hardware acceleration flags if available
455
- cmd.extend(self.hwaccel_flags)
456
-
457
- # Input source (background) - simplified for preview
458
- if self.background_image:
459
- # For preview, use the original image without resizing to save time
460
- self.logger.debug(f"Using original background image for preview: {self.background_image}")
461
- cmd.extend([
462
- "-loop", "1", # Loop the image
463
- "-i", self.background_image,
464
- ])
465
- # Build video filter with scaling and ASS subtitles
466
- video_filter = f"scale={width}:{height}:force_original_aspect_ratio=decrease,pad={width}:{height}:(ow-iw)/2:(oh-ih)/2,{self._build_ass_filter(ass_path)}"
467
- else:
468
- self.logger.debug(
469
- f"Using solid {self.background_color} background "
470
- f"with resolution: {width}x{height}"
471
- )
472
- cmd.extend([
473
- "-f", "lavfi",
474
- "-i", f"color=c={self.background_color}:s={width}x{height}:r=24",
475
- ])
476
- # Build video filter with just ASS subtitles (no scaling needed)
477
- video_filter = self._build_ass_filter(ass_path)
478
-
479
- cmd.extend([
480
- "-i", audio_path,
481
- "-vf", video_filter, # Apply the video filter
482
- "-c:a", "aac", # Use AAC for audio compatibility
483
- "-b:a", "96k", # Reduced audio bitrate for faster encoding
484
- "-c:v", self.video_encoder,
485
- ])
486
-
487
- # Add encoder-specific settings for preview with maximum speed priority
488
- if self.nvenc_available:
489
- # NVENC settings optimized for maximum speed
490
- cmd.extend([
491
- "-preset", "p1", # Fastest NVENC preset
492
- "-tune", "ll", # Low latency
493
- "-rc", "cbr", # Constant bitrate for speed
494
- "-b:v", "800k", # Lower bitrate for speed
495
- "-profile:v", "baseline", # Most compatible profile
496
- "-level", "3.1", # Lower level for speed
497
- ])
498
- self.logger.debug("Using NVENC encoding with maximum speed settings for preview video generation")
499
- else:
500
- # Software encoding with maximum speed priority
501
- cmd.extend([
502
- "-profile:v", "baseline", # Most compatible H.264 profile
503
- "-level", "3.0", # Compatibility level
504
- "-preset", "superfast", # Even faster than ultrafast for preview
505
- "-tune", "fastdecode", # Optimize for fast decoding
506
- "-b:v", "600k", # Lower base bitrate for speed
507
- "-maxrate", "800k", # Lower max bitrate
508
- "-bufsize", "1200k", # Smaller buffer size
509
- "-crf", "28", # Higher CRF for faster encoding (lower quality but faster)
510
- ])
511
- self.logger.debug("Using software encoding with maximum speed settings for preview video generation")
512
-
513
- cmd.extend([
514
- "-pix_fmt", "yuv420p", # Required for browser compatibility
515
- "-movflags", "+faststart+frag_keyframe+empty_moov+dash", # Enhanced streaming with dash for faster start
516
- "-g", "48", # Keyframe every 48 frames (2 seconds at 24fps) - fewer keyframes for speed
517
- "-keyint_min", "48", # Minimum keyframe interval
518
- "-sc_threshold", "0", # Disable scene change detection for speed
519
- "-threads", "0", # Use all available CPU threads
520
- "-shortest", # End encoding after shortest stream
521
- "-y" # Overwrite output without asking
522
- ])
523
-
524
- # Add output path
525
- cmd.append(output_path)
526
-
527
- return cmd
528
-
529
494
  def _get_video_codec(self) -> str:
530
495
  """Determine the best available video codec (legacy method - use video_encoder instead)."""
531
496
  # This method is kept for backwards compatibility but is deprecated