stable-ts
Whisper-based transcription with forced alignment and audio indexing, including a mode that loads audio in 30s chunks for near-streaming subtitle generation.
Link
Related resources
- WhisperXASR pipeline producing word-level timestamps via wav2vec2 forced alignment plus speaker diarization, useful for accurate subtitle cue timin…
- AutoSubtitle — Whisper subtitle GUI with burn-inPyQt5 GUI that generates bilingual subtitles using faster-whisper and Silero VAD with LLM translation and FFmpeg burn-in/hardcode.
- STL2TTML — EBU STL to TTML/WebVTT converterJava tool converting EBU STL (Tech 3264) binary subtitle files to TTML and WebVTT for streaming delivery.
- SCF — Subtitling Conversion Framework (EBU)IRT's Subtitling Conversion Framework converting between EBU STL, EBU-TT Part 1 (Tech 3350/3360) and EBU-TT-D (Tech 3380) with strict confo…
- subgen — Whisper Auto-Subtitles for Media ServersAuto-subtitle generator using Whisper (stable-ts + faster-whisper) for Jellyfin/Plex/Emby/Bazarr, CPU or CUDA.
- ITU-T P.1203 reference implementationOfficial Python reference implementation of the ITU-T P.1203 HTTP adaptive streaming QoE model (modes 0-3), outputting per-second and integ…
- butteraugli (Rust port)Pure Rust port of Butteraugli from libjxl with XYB color, visual masking, and multi-scale bands, validated to within 0.001% of the referenc…
- SimpleVQADeep-learning no-reference video quality assessment for user-generated content, in PyTorch with SlowFast feature extraction.
- AutoShotCVPR-NAS 2023 shot boundary detection model with a NAS-optimized architecture and the new SHOT dataset (853 videos, 11,606 annotations).