This is an on-going project. it is a modified version of Higgs-Boson audio tokenizer, you can fully train it. all scripts have been tested.
a Few notes however:
-
this is not backward compatible with the original checkpoint (I think you can tweak it to be, but you have to adhere to Boson community license if you do.)
-
I highly recommend you to pretrain the model without the mel and adversarial setup first. it saves you a significant amount of compute, time and speed-up your convergence. raise the batch size as much as you can before the adversarial phase.
-
for the semantic teacher, I am using utter-project/mHuBERT-147 which has a good multilingual support. if you want the original setup you can change it in the config.
-
The loss weights and hyperparameters may not be ideal, feel free to play around with different values.
I will train a checkpoint on a larger enough dataset one of these days after figuring out a few things first. but the setup is solid.
1python train_boson_mixed_precision.py --data_csv "yourdata.csv" \ # full path to your audio files, the format can be anything .mp3 .wav .ogg etc.
2 --config config.json --batch_size 42 \
3 --use_mixed_precision \
4 --use_discriminator
