Automatic Speech Recognition
ESPnet
multilingual
audio
speech-translation

TypeError when attempting to use the model

#1
by cifkao - opened

I'm excited to try the model, but cannot get it to work. I installed the latest version of espnet from master and I used the snippet provided under the "Use in ESPnet" button:

from espnet2.bin.asr_inference import Speech2Text

model = Speech2Text.from_pretrained(
  "espnet/owsm_v3.1_ebf"
)

I'm getting the following error:
```python

TypeError Traceback (most recent call last)
Cell In[1], line 3
1 from espnet2.bin.asr_inference import Speech2Text
----> 3 model = Speech2Text.from_pretrained(
4 "espnet/owsm_v3.1_ebf"
5 )

File ~/mambaforge/envs/espnet/lib/python3.10/site-packages/espnet2/bin/asr_inference.py:679, in Speech2Text.from_pretrained(model_tag, **kwargs)
676 d = ModelDownloader()
677 kwargs.update(**d.download_and_unpack(model_tag))
--> 679 return Speech2Text(**kwargs)

TypeError: Speech2Text.init() got an unexpected keyword argument 's2t_train_config'

Can you please provide the correct code to use the model?
ESPnet org

Thanks for reporting the issue.
See https://github.com/espnet/espnet/discussions/5723

That works, thank you!

cifkao changed discussion status to closed

Sign up or log in to comment