Telegram-Zalo/zac2022-lyric-alignment
Solution for Zalo AI Challenge 2022 - Lyrics Alignment
Combines source separation (Demucs) with fine-tuned Wav2Vec2 acoustic modeling and dynamic programming-based forced alignment to map lyrics to precise audio timestamps. The pipeline includes data augmentation through random segment merging, custom vocabulary adaptation for Vietnamese, and character-level CTC training followed by viterbi-style alignment to extract word-level temporal boundaries. Designed for the Zalo AI Challenge 2022 with reproducible training scripts and checkpoint downloads.
No commits in the last 6 months.
Stars
68
Forks
18
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 05, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Telegram-Zalo/zac2022-lyric-alignment"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
mikezzb/lyrics-sync
A deep learning lyrics-to-audio alignment system, generating synchronized lyrics from a song and...
theelderemo/genius-lyrics-cleaned-dataset
3.17M cleaned & deduplicated English song lyrics from Genius: title, artist, genre tag, year,...
AmirHaytham/LyricMind-AI
LyricMind-AI: Intelligent Lyrics Generation with Deep Learning
schak04/karaoke-app
A simple CLI-based karaoke app that fetches lyrics from the Genius API, downloads song audio...
RicardoRibeiroRodrigues/MusicLyricsGenerator
Generative AI solutions for generating music lyrics.