guxm2021/ALT_SpeechBrain
[ISMIR 2022] Transfer Learning of wav2vec 2.0 for Automatic Lyric Transcription
This project helps music professionals, researchers, and anyone working with vocal recordings to accurately transcribe sung lyrics into text. It takes audio files of singing as input and outputs the corresponding lyrics, even when the singing is difficult to understand. It is designed for those who need to convert sung vocals into written words for analysis, indexing, or other applications.
No commits in the last 6 months.
Use this if you need to automatically generate accurate text transcripts from vocal performances, especially when dealing with large volumes of audio or challenging singing styles.
Not ideal if you primarily need to transcribe spoken dialogue rather than sung lyrics, as dedicated speech-to-text tools might be more suitable.
Stars
49
Forks
6
Language
Python
License
Apache-2.0
Category
Last pushed
May 07, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/guxm2021/ALT_SpeechBrain"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
subhasis-ai/Hindi-ASR-Wav2Vec2
This repository demonstrates development of Hindi ASR model using transformers.
guxm2021/MM_ALT
[MM 2022] MM-ALT: A Multimodal Automatic Lyric Transcription System (Oral, Top paper award)
jvel07/wav2vec2_patho
Fine-tuning wav2vec2 to for Pathological Speech Processing
hammaad2002/ASRAdversarialAttacks
An ASR (Automatic Speech Recognition) adversarial attack repository.
maximkm/DLA_ASR_HW
ASR pytorch project