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.
Python
Stargazers
- Adagio112
- alefiuryUniversidade Federal de Goiás
- ArthurZucker@huggingface
- atuxhe
- BarryAzuki2233
- charlesliucnTsinghua University
- clementapaENS Paris-Saclay
- ddiv-lee
- Durgesh92I AM +
- dytan
- EmreOzkoseHacettepe University
- fly51flyPRIS
- iljab
- innnky
- iwaterChina
- JackKCWong
- JinchaoLoveThe Chinese University of Hong Kong
- jqueguiner@gladiaio
- khursani8Kuala Lumpur
- kunatoKUNANA AI
- MoodrammerCairo University
- nshmyrevAlpha Cephei Inc
- psycho811
- qgzangUSTC
- rishikksh20Dubpro.ai
- seastar105@kakao
- shaun95
- singhranjodhIndia
- straberrywakaka
- WikidepiaIndonesia
- wxlsummerUniversity of Edinburgh
- xrickTaiwan, Taipei
- xuanhan863Los Angeles, USA
- younesbelkada@huggingface
- ytf-philp
- zw76859420Trip