Whisper model- Audio Classification
ValueError Traceback (most recent call last)
in <cell line: 5>()
3 num_labels = len(id2label)
4
----> 5 model = AutoModelForAudioClassification.from_pretrained(
6 āopenai/whisper-baseā,
7 num_labels=num_labels,
/usr/local/lib/python3.10/dist-packages/transformers/models/auto/auto_factory.py in from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs)
465 token = hub_kwargs.pop(ātokenā, None)
466 use_auth_token = hub_kwargs.pop(āuse_auth_tokenā, None)
ā 467 if use_auth_token is not None:
468 warnings.warn(
469 āThe use_auth_token argument is deprecated and will be removed in v5 of Transformers. Please use token instead.ā,
ValueError: Unrecognized configuration class <class ātransformers.models.whisper.configuration_whisper.WhisperConfigā> for this kind of AutoModel: AutoModelForAudioClassification.
Model type should be one of ASTConfig, Data2VecAudioConfig, HubertConfig, SEWConfig, SEWDConfig, UniSpeechConfig, UniSpeechSatConfig, Wav2Vec2Config, Wav2Vec2ConformerConfig, WavLMConfig.