GitHub / ASR-project / Multilingual-PR
Phoneme Recognition using pre-trained models Wav2vec2, HuBERT and WavLM. Throughout this project, we compared specifically three different self-supervised models, Wav2vec (2019, 2020), HuBERT (2021) and WavLM (2022) pretrained on a corpus of English speech that we will use in various ways to perform phoneme recognition for different languages with a network trained with Connectionist Temporal Classification (CTC) algorithm.
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ASR-project%2FMultilingual-PR
Stars: 171
Forks: 13
Open issues: 1
License: None
Language: Python
Size: 3.47 MB
Dependencies parsed at: Pending
Created at: about 3 years ago
Updated at: about 1 year ago
Pushed at: almost 3 years ago
Last synced at: about 1 year ago
Topics: asr, common-voice, deep-learning, huggingface, huggingface-transformers, phone-recognition, self-supervised-learning, speech-processing, speech-recognition, wandb