Wav2Vec2_PyCTCDecode
Wav2Vec2_PyCTCDecode copied to clipboard
Small repo describing how to use Hugging Face's Wav2Vec2 with PyCTCDecode
Hi, the speed of decoding is too slow, about 5 seconds per utterance. How can I use multi-thread or multi-cpu to decode?
Thanks @patrickvonplaten for this repo, it really helped a lot! Just a question here, what is the best language model for CTC decoding? is it a character-level or word-level language...
I followed the tutorial and installed kenlm inside the subfolder kenlm and created the polish.arpa file and updated it. I get the following error when running ./eval.py --language polish --path_to_ngram...