sebastjan/reels-app
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit Graph

  • 68247bb84c Integrate ElevenLabs Scribe (best multilingual STT 2026) sebastjan 2026-04-29 12:03:40 +00:00
  • 3ffa9740f0 Revert "Add Groq Whisper API integration (200x faster than local CPU)" sebastjan 2026-04-29 11:19:31 +00:00
  • 6a8f87b4a2 Revert "Filler detection: trim clip before la-la-la / instrumental medbridge" sebastjan 2026-04-29 11:19:31 +00:00
  • 4488717f6f Filler detection: trim clip before la-la-la / instrumental medbridge sebastjan 2026-04-29 11:17:16 +00:00
  • 5c53a27d33 Add Groq Whisper API integration (200x faster than local CPU) sebastjan 2026-04-29 11:08:15 +00:00
  • 60765ad84c Anti-hallucination: filename hint to LLM + beam search + silence threshold sebastjan 2026-04-29 10:48:55 +00:00
  • 05fb0081c6 Fix preview cutoff + sticky left panel sebastjan 2026-04-29 10:24:23 +00:00
  • 0ca33be6ac Fix: clip_range source dynamic from LLM result instead of hardcoded 'claude' OpenClaw Agent 2026-04-29 09:49:58 +00:00
  • e350352883 Fix: Gemini 3.1 Pro thinking model needs 32k maxOutputTokens (was 4096 → MAX_TOKENS truncation) OpenClaw Agent 2026-04-29 09:03:53 +00:00
  • 534d710e8a Auto-resume jobs interrupted by container restart sebastjan 2026-04-29 08:52:16 +00:00
  • 32baf9cd45 Auto-resume: cleanup stuck jobs on container startup + GEMINI_API_KEY env sebastjan 2026-04-29 08:43:31 +00:00
  • ec71c54570 Upgrade to Sonnet 4.6 + add Gemini 3.1 Pro support sebastjan 2026-04-29 08:26:27 +00:00
  • 9faa224885 Upgrade Claude model: Haiku 4.5 → Sonnet 4.6 for better Slavic language transcript correction sebastjan 2026-04-29 08:22:10 +00:00
  • 69fb2f5ce8 Upgrade default Whisper model: small/medium → large-v3 for much better Slovenian/Slavic transcription accuracy sebastjan 2026-04-29 08:20:18 +00:00
  • 4bc5ac6756 Major: Claude post-processing of Whisper transcript sebastjan 2026-04-29 08:13:33 +00:00
  • 4e123bdabc UI: hide lang/model dropdowns — both are fully automatic now (3-sample lang detection + medium default model) sebastjan 2026-04-29 08:03:22 +00:00
  • af3c933c78 Robust language detection + anti-hallucination sebastjan 2026-04-29 07:59:20 +00:00
  • c870d80726 Fix: extend clip if ends mid-vocal (no chorus cut-off), DejaVu Sans font (supports SLO/HR/BS chars), auto-upgrade to medium Whisper model for Slavic languages sebastjan 2026-04-29 07:35:00 +00:00
  • 5d5e169f9d Disable Whisper VAD filter — was dropping vocal segments in songs creating gaps in subtitles sebastjan 2026-04-29 07:07:29 +00:00
  • a04811bdc9 Add Claude LLM analysis: sends full transcript to Claude API for true song structure understanding (refrain detection across all repetitions, not just local heuristic) sebastjan 2026-04-29 06:55:41 +00:00
  • e072eec362 Fix: handle Whisper transcribe failure for instrumental-only audio (fallback to empty transcript) sebastjan 2026-04-29 06:33:52 +00:00
  • 33a138af9e Fix: force native Python bool/float for JSON serialization (numpy types) sebastjan 2026-04-29 06:23:41 +00:00
  • 8512076b91 Major: smart selection pipeline (analyze.py) + audio fade + multi-lang auto-detect sebastjan 2026-04-29 06:21:35 +00:00
  • 81edd24ca3 Subtitles: smaller font 56px (was 84), higher position MarginV=400, side margins 80px for safe zone sebastjan 2026-04-29 06:09:26 +00:00
  • ba787744a6 Subtitles: cap chunk duration at 2.5s, split long lines into multiple time slices for faster reels pacing sebastjan 2026-04-29 05:59:36 +00:00
  • e001387a89 Subtitles: convert SRT to ASS directly with PlayResY=1920 for predictable scaling instead of unreliable force_style sebastjan 2026-04-28 18:09:53 +00:00
  • 28d933c916 Subtitles: UPPERCASE + position lower (MarginV=320 for 1080x1920) + bigger font sebastjan 2026-04-28 17:40:48 +00:00
  • d36893bf2d FIX CRITICAL: reload job dict after find_chorus update so reframe gets new start/duration values sebastjan 2026-04-28 17:33:11 +00:00
  • 15ef4888a1 Debug: log exact clip.py cmd in job + clip.py logs run_clip args sebastjan 2026-04-28 17:28:10 +00:00
  • bc3fe1f9d4 Add explicit FFmpeg trim command logging + duration verification sebastjan 2026-04-28 17:17:11 +00:00
  • 8eaef029e2 Find chorus: weight repetitive short phrases (like 'Ohne dich x5') as strong chorus signal sebastjan 2026-04-28 16:57:45 +00:00
  • c17578521a Fix find_chorus: RMS energy parser was broken (no pts_time available), now syntheses timestamps; energy weight x10 (refren je glasnejši) sebastjan 2026-04-28 16:55:51 +00:00
  • 64e8854cea Track mode: more sensitive face detection + longer smoothing window sebastjan 2026-04-28 16:45:13 +00:00
  • 400f6dbb6d Fix: limit FFmpeg crop expression to 20 sample points (was overflowing 4KB limit) sebastjan 2026-04-28 16:32:26 +00:00
  • bf7ced5c7b Reset upload form also after failed jobs (so next upload works) sebastjan 2026-04-28 16:29:39 +00:00
  • 2e337ff079 Fix: shutil import was inside finally block, causing NameError when shutil.move was called sebastjan 2026-04-28 16:22:39 +00:00
  • c34e4aa376 UX: Live progress panel below upload form, stable progress bar, inline preview/download sebastjan 2026-04-28 16:19:40 +00:00
  • 6e2a13d8a3 Fix cross-device link error: use shutil.move instead of os.replace sebastjan 2026-04-28 16:15:20 +00:00
  • 02ec6f81f2 Add Deno runtime for yt-dlp YouTube nsig challenge solving sebastjan 2026-04-28 16:05:09 +00:00
  • e304b08d7b Add nodejs for yt-dlp JS challenge solver, remove anonymous VOLUME sebastjan 2026-04-28 15:51:57 +00:00
  • 83734dfdc5 Upgrade yt-dlp to nightly for new YouTube nsig algorithm support sebastjan 2026-04-28 15:48:39 +00:00
  • 47509b4f06 Add cookies support to yt_download.py for YouTube bot detection bypass sebastjan 2026-04-28 15:47:59 +00:00
  • 8e41bf21f6 Fix: create empty static/ in container instead of COPY (was empty in git) sebastjan 2026-04-28 15:34:50 +00:00
  • 30b969e4b8 Initial: reels clipper app sebastjan 2026-04-28 15:28:22 +00:00