VoxCeleb2 https://www.robots.ox.ac.uk/~vgg/data/voxceleb/vox2.html
VoxBlink2 https://voxblink2.github.io/
3D-Speaker https://3dspeaker.github.io
MeetCLR2022 https://MeetCLRchallenge.github.io/MeetCLRchallenge2022/data.html
RetinaFace for Face Detection https://github.com/biubug6/Pytorch_Retinaface
Towards Fast, Accurate and Stable 3D Dense Face Alignment https://github.com/cleardusk/3DDFA_V2
FSMN-VAD in FunASR https://huggingface.co/funasr/fsmn-vad
Musan https://www.openslr.org/17/
RIRS https://www.openslr.org/28/
LRS3 https://mmai.io/datasets/lip_reading/
CNCVS https://cnceleb.org/
AV-HuBERT https://github.com/facebookresearch/av_hubert
Auto-AVSR https://github.com/mpc001/auto_avsr
Whisper https://github.com/openai/whisper
NeRFace https://github.com/gafniguy/4D-Facial-Avatars
CAM++ (Speech Verification) https://www.modelscope.cn/models/iic/speech_campplus_sv_zh-cn_16k-common
CAM++ (Speaker Diarization) https://www.modelscope.cn/models/iic/speech_campplus_speaker-diarization_common
ERestNet https://modelscope.cn/models/iic/speech_eres2netv2_sv_zh-cn_16k-common/summary
WavLM https://huggingface.co/docs/transformers/model_doc/wavlm#wavlm
Wav2Vec 2.0 https://huggingface.co/docs/transformers/model_doc/wav2vec2
XLS-R https://huggingface.co/docs/transformers/model_doc/xls_r
SynVSR https://github.com/KAIST-AILab/SyncVSR/tree/weight-audio-v1
CNCVS, CNVSRC-single, CNVSRC-multi, CNVSRC2023 https://cnceleb.org/competition
MSDWild https://github.com/X-LANCE/MSDWILD
CMLR https://www.vipazoo.cn/CMLR.html
Funasr https://github.com/modelscope/FunASR.git
Qwen2.5 https://github.com/QwenLM/Qwen2.5.git
Aishell4 https://www.openslr.org/111/
Alimeeting https://www.openslr.org/119/
LRW https://www.robots.ox.ac.uk/~vgg/data/lip_reading/lrw1.html
Pyroomacoustic https://github.com/LCAV/pyroomacoustics
FRAM-RIR https://github.com/tencent-ailab/FRA-RIR
Lipreading using TCN https://github.com/mpc001/Lipreading_using_Temporal_Convolutional_Networks
Face-Alignment https://github.com/1adrianb/face-alignment
gpurir https://github.com/DavidDiazGuerra/gpuRIR
wespeaker https://github.com/wenet-e2e/wespeaker/blob/master/docs/pretrained.md
pyannote https://huggingface.co/pyannote