fengshi-cherish / wespeaker

WeSpeaker

WeSpeaker mainly focuses on speaker embedding learning, with application to the speaker verification task. We support online feature extraction or loading pre-extracted features in kaldi-format.

Installation && Run

• Create Conda env: pytorch version >= 1.10.0 is required !!!

conda create -n wespeaker python=3.9
conda activate wespeaker
conda install pytorch=1.10.1 torchaudio=0.10.1 cudatoolkit=11.3 -c pytorch -c conda-forge
pip install -r requirements.txt

• Run voxceleb recipe

cd examples/voxceleb/v2
bash run.sh --stage 2 --stop-stage 4

Dataset Support

• Voxceleb dataset

Support list:

• Model (SOTA models):
  • Standard X-vector
  • ResNet
  • ECAPA_TDNN
• Pooling functions
  • TAP(mean) / TSDP(std) / TSTP(mean+std)
  • Attentive statistics pooling (ASTP)
  • Learnable Dictionary Encoding (LDE)
• Criteria
  • softmax
  • sphere
  • add_margin (AM-softmax)
  • arc_margin (AAM-softmax)
• Scoring:
  • cosine scoring
  • python plda scoring
  • score normalization (AS-Norm)
• Online Augmentation：
  • rir+noise
  • speed perturb
  • specaug
• Literature
  • Awesome speaker papers

Looking for contributors

If you are interested to contribute, feel free to contact @wsstriving or @robin1001