tabahi/bournemouth-forced-aligner
Extract phoneme-level timestamps from speeh audio.
Combines wav2vec2 speech representations with DTW (dynamic time warping) to align phonemes without requiring forced-alignment training data or phoneme inventories. Supports 80+ languages through language presets, outputs millisecond-precision timestamps with confidence scores, and exports to Praat TextGrid or JSON formats for downstream speech processing and TTS workflows.
121 stars and 1,657 monthly downloads. Used by 1 other package. Available on PyPI.
Stars
121
Forks
12
Language
Python
License
GPL-3.0
Category
Last pushed
Feb 28, 2026
Monthly downloads
1,657
Commits (30d)
0
Dependencies
9
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/tabahi/bournemouth-forced-aligner"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
fgnt/meeteval
MeetEval - A meeting transcription evaluation toolkit
kahne/fastwer
A PyPI package for fast word/character error rate (WER/CER) calculation
readbeyond/aeneas
aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka...
wq2012/SimpleDER
A lightweight library to compute Diarization Error Rate (DER).
analyticsinmotion/werpy
🐍📦 Ultra-fast Python package for calculating and analyzing the Word Error Rate (WER). Built for...