🏆 #3,738 overall#453 of 795 in Speech Recognition

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.

$ git clone https://github.com/ASR-project/Multilingual-PR.git
GitHub social preview for ASR-project/Multilingual-PR
Stars
270
270
This week
0 ★
Forks
24
24
Language
Python
License
None
Created
Feb 25, 2022
4.7 years old
Last push
May 9, 2022

Stars, last 17 days

Oct 28, 2026 → Nov 16, 2026
★ 270▲ +0★ 270

Categories

GitHub topics

More in Speech Recognition

Speech Recognition

PaddlePaddle/PaddleSpeech

▲ +7 ★ this week

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

PythonApache-2.0updated Aug 12, 2026
GitHub ↗★ 12.7K⑂ 2K
Speech Recognition

speechbrain/speechbrain

▲ +12 ★ this week

A PyTorch-based Speech Toolkit

🤖 Language Models
PythonApache-2.0updated Oct 14, 2026
GitHub ↗★ 11.9K⑂ 1.8K
Speech Recognition

coqui-ai/STT

▲ +1 ★ this week

🐸STT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.

C++MPL-2.0updated Mar 11, 2024
GitHub ↗★ 2.6K⑂ 295
Speech Recognition

nyrahealth/CrisperWhisper🔥 active

▲ +14 ★ this week

Controllable Transcription. Verbatim ( every, filler, pause, stutter, vocal sound) , or intended ( what the speaker meant to say, optimized for readability) with word-level timestamps.

PythonOtherupdated Nov 11, 2026
GitHub ↗★ 1.5K⑂ 97

Data from GitHub · snapshot Nov 16, 2026