search

sanchit-gandhi / seq2seq-speech

Repository for fine-tuning Transformers 🤗 based seq2seq speech models in JAX/Flax.
34 stars 6 forks source link

[CTC] Fix bug in model-tokenizer vocab size mismatch #36

Closed sanchit-gandhi closed 2 years ago

sanchit-gandhi commented 2 years ago

(Hopefully!) fixes #28 based on the solution presented in https://github.com/sanchit-gandhi/seq2seq-speech/issues/28#issuecomment-1127755851