I am trying to train a speech-to-text model for the Armenian language. After I am using the Nvidia NeMo toolkit. After training the acoustic model I used provided NeMo/scripts/asr_language_modeling/ngram_lm/train_kenlm.py file to train the language model and it gave the error AttributeError: 'EncDecCTCModel' object has no attribute 'tokenizer', but there are many pre-trained QuartzNet models that support LM. How can I train the language model for QuartzNet, or are there better models to train and use with LM?
Asked
Active
Viewed 24 times
0
arm
- 56
- 1
- 12