oseiskar/autosubsync
Automatically synchronize subtitles with audio using machine learning
Detects speech in audio using logistic regression on spectrogram features, then searches for optimal linear time transformations (shift and speed correction) by matching subtitle timings to speech probability distributions. Supports all FFmpeg-compatible video formats and SRT subtitles regardless of language, with typical synchronization accuracy of ~0.15 seconds and a Python API for batch processing.
453 stars and 640 monthly downloads. No commits in the last 6 months. Available on PyPI.
Stars
453
Forks
38
Language
Python
License
MIT
Category
Last pushed
Jun 21, 2023
Monthly downloads
640
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/oseiskar/autosubsync"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
SYSTRAN/faster-whisper
Faster Whisper transcription with CTranslate2
FL33TW00D/whisper-turbo
Cross-Platform, GPU Accelerated Whisper 🏎️
machinelearningZH/audio-transcription
Transcribe any audio or video file. Edit and view your transcripts in a standalone HTML editor.
saharmor/whisper-playground
Build real time speech2text web apps using OpenAI's Whisper https://openai.com/blog/whisper/
shhossain/BanglaSpeech2Text
BanglaSpeech2Text: An open-source offline speech-to-text package for Bangla language. Fine-tuned...