KeyError: 'wav2vec2-conformer'
#1
by
codekiln
- opened
config.json has this:
"model_type": "wav2vec2-conformer",
Locally, when trying to instantiate using the Auto API, I get a KeyError for this value.
model = AutoModelForAudioClassification.from_pretrained("juliensimon/wav2vec2-conformer-rel-pos-large-finetuned-speech-commands")
...
File "C:\Users\Myr\anaconda3\envs\s89-dl\lib\site-packages\transformers\models\auto\auto_factory.py", line 423, in from_pretrained
config, kwargs = AutoConfig.from_pretrained(
File "C:\Users\Myr\anaconda3\envs\s89-dl\lib\site-packages\transformers\models\auto\configuration_auto.py", line 672, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "C:\Users\Myr\anaconda3\envs\s89-dl\lib\site-packages\transformers\models\auto\configuration_auto.py", line 387, in __getitem__
raise KeyError(key)
KeyError: 'wav2vec2-conformer'
Any tips?
Hi,
no issue here. Have you tried upgrading the transformers library? This is a fairly recent model, it wouldn't work with older versions.
juliensimon
changed discussion status to
closed