search

HarryVolek / PyTorch_Speaker_Verification

PyTorch implementation of "Generalized End-to-End Loss for Speaker Verification" by Wan, Li et al.
BSD 3-Clause "New" or "Revised" License
575 stars 166 forks source link

Pre-trained model #7

Closed strawberrypie closed 5 years ago

strawberrypie commented 5 years ago

Hi! Do you have any plans on sharing a pre-trained model on TIMIT?

HarryVolek commented 5 years ago

Hi, I do not plan on uploading weights.

ahsanmemon commented 5 years ago

There is a model.model file in your repository.

  1. Do I have to create a model of my own if I am using a personalized dataset.
  2. How do I create the file (I mean, train the embeddings)

I am relatively new to the d-vector ecosystem here. Been only working with the i-vectors.