feldberlin/timething
Timething is a library for aligning text transcripts with their audio recordings.
Leverages Wav2Vec CTC models from Hugging Face for forced alignment, producing character and word-level timestamps with confidence scores via the PyTorch forced alignment approach. Supports both long-form media (podcasts, audiobooks) and machine learning workflows, with optional audio re-cutting based on alignment results. Handles multiple audio formats and 12+ languages, running efficiently on CPUs or GPUs with configurable batch processing.
130 stars and 152 monthly downloads. No commits in the last 6 months. Available on PyPI.
Stars
130
Forks
14
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Dec 03, 2024
Monthly downloads
152
Commits (30d)
0
Dependencies
8
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/feldberlin/timething"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
ieasybooks/tafrigh
تفريغ النصوص وإنشاء ملفات SRT و VTT باستخدام نماذج Whisper وتقنية wit.ai.
botbahlul/autosrt
A python script COMMAND LINE utility to AUTO GENERATE SUBTITLE FILE (using free Google Speech...
botbahlul/PyAutoSRT
PySimpleGUI based DESKTOP APP to AUTO GENERATE SUBTITLE FILE (using free Google Speech...
abhirooptalasila/AutoSub
A CLI script to generate subtitle files (SRT/VTT/TXT) for any video using either DeepSpeech or Coqui
cpfair/quran-align
Word-accurate timestamps for Qur'anic audio.