Error when load the model by "Speech2Text.from_pretrained"

#1
by Ht-zhang-xianyu - opened

Hello, I try to use the pre-trained model "chai_librispeech_asr_train_transducer_v2_raw_en_bpe5000_sp " by following the command with
'''
from espnet2.bin.asr_inference import Speech2Text

model = Speech2Text.from_pretrained(
"chaitu619/chai_librispeech_asr_train_transducer_v2_raw_en_bpe5000_sp"
)
'''
but some messages like "AttributeError: 'Namespace' object has no attribute 'encoder'"
how to fix that?

Sign up or log in to comment