How to quickly train the model based on the original model for the audio data of the new speaker？ - Githubissues

philipperemy / deep-speaker

Deep Speaker: an End-to-End Neural Speaker Embedding System.

MIT License

905 stars 241 forks source link

How to quickly train the model based on the original model for the audio data of the new speaker？ #59

Closed joewale closed 4 years ago

joewale commented 4 years ago

How to quickly train the model based on the original model for the audio data of the new speaker？

philipperemy commented 4 years ago

@joewale I would say it's kinda difficult but I've never tried. You can re run the training commands on your dataset+Libri. First, make sure it's in the LibriSpeech format otherwise the python code won't work.