I have been trying to finetune Turbo model for Russian language using RUSLAN dataset (precisely the first 800 files of it due to hardware restrictions (still amounting to around 1 hour of pure noisless audio)), but encountered loss around multiple 1e+12 (meaning loss is always around 10 bil to multiple trillions).
Tried with stock tokenizer.json and with tokenizer where i moved Russian characters to 'model''vocab' from 'added_tokens'. Checked metadata encoding to avoid transcription being random characters. Also tried adding max_grad_norm = 1.0 to training parameters which bore no difference.
Don't know if i am doing anything wrong or data is not suitable for training (though dataset is specifically built for TTS training purposes).
I have been trying to finetune Turbo model for Russian language using RUSLAN dataset (precisely the first 800 files of it due to hardware restrictions (still amounting to around 1 hour of pure noisless audio)), but encountered loss around multiple 1e+12 (meaning loss is always around 10 bil to multiple trillions).
Tried with stock tokenizer.json and with tokenizer where i moved Russian characters to 'model''vocab' from 'added_tokens'. Checked metadata encoding to avoid transcription being random characters. Also tried adding max_grad_norm = 1.0 to training parameters which bore no difference.
Don't know if i am doing anything wrong or data is not suitable for training (though dataset is specifically built for TTS training purposes).