wavlm 开源项目推荐（58 个）

yl4579 /StyleTTS2

StyleTTS 2：通过风格扩散和大型语音语言模型对抗训练迈向人类水平的文本转语音

s3prl /s3prl

自监督语音预训练与表示学习工具包

wenet-e2e /wespeaker

面向研究和生产的说话人验证、识别和拨号工具包

lucadellalib /focalcodec

A low-bitrate single-codebook 16 / 24 kHz speech codec based on focal modulation

lucadellalib /audiocodecs

A collections of audio codecs with a standardized API

mjhydri /Singing-Vocal-Beat-Tracking

This repo contains the source code of the first deep learning-base singing voice beat tracking system. It leverages WavLM and DistilHuBERT pre-trained speech models to create vocal embeddings and trains linear multi-head self-attention layers on top of them to extract vocal beat activations. Then, it uses HMM decoder to infer signing beats and t…

lucadellalib /discrete-wavlm-codec

A neural speech codec based on discrete WavLM representations

lucadellalib /zipcodec

A 6.25 Hz, 0.80 kbit/s streaming neural audio codec based on WavLM

Amir-Ivry /MAPSS-measures

The code for the MAPSS measures for source separation evaluation (ICLR, 2026)

MattyB95 /Jabberjay

🦜 Synthetic Voice Detection

bunyaminergen /WavLMMSDD

This repository combines `WavLM`, a powerful speech representation model from Microsoft, with `MSDD` (Multi-Scale Diarization Decoder), a state-of-the-art approach for speaker diarization from Nvidia.

sadPororo /LAP

Rethinking Leveraging Pre-Trained Multi-Layer Representations for Speaker Verification, ISCA Interspeech 2025

sadPororo /L-TDNN

Layer-aware TDNN: Speaker Recognition Using Multi-Layer Features from Pre-Trained Models, to appear in ICAIIC 2026

Sarasadeghii /Sharif-WavLM

In this repository, the wavLM model is used for quality and poor quality data for speaker verification task, and the PyCM library is used for evaluation.

alessandropec /data_driven_ai_voice_cloning

This repository contain the code of the main part of my master thesis degree at Politecnico di Torino in Data science & Engineering

theolepage /wavlm_ssl_sv

SOTA method for self-supervised speaker verification leveraging a large-scale pretrained ASR model.

HoppouAI /ApexSVC

Zero shot singing voice conversion, whats better to make than this on a Monday?

aaivu /KuralHub

Speech emotion recognition (SER) datasets for 70 languages and a benchmark of 11 speech models (HuBERT, wav2vec 2.0, WavLM, Whisper) in 29 languages. Interspeech 2026.

zhu00121 /Universal-representation-dynamics-of-deepfake-speech

This repo contains code used in the paper "Characterizing the temporal dynamics of universal speech representations for generalizable deepfake detection"

bunyaminergen /WavLMRawNetXSVBase

WavLM Large + RawNetX Speaker Verification Base: End-to-End Speaker Verification Architecture