How to train?
#6
by
psk
- opened
I want to train this codec for different language. is it possible to open source the code for training?
Yes, codec trained on 150k hours of multilingual speech data, including Emilia (En/Zh/De/Fr/Ja/Ko) and MLS (En/Fr/De/Nl/Es/It/Pt/Pl). https://github.com/zhenye234/X-Codec-2.0