Wav2Vec2Processor:
- feature_extractor: Wav2Vec2FeatureExtractor {
"do_normalize": true,
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
"feature_size": 1,
"padding_side": "right",
"padding_value": 0.0,
"return_attention_mask": true,
"sampling_rate": 16000
}
- tokenizer: Wav2Vec2CTCTokenizer(name_or_path='audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim', vocab_size=0, model_max_length=1000000000000000019884624838656, is_fast=False, padding_side='right', truncation_side='right', special_tokens={'bos_token': '', 'eos_token': '', 'unk_token': '', 'pad_token': ''}, clean_up_tokenization_spaces=True), added_tokens_decoder={
0: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
1: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
2: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
3: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
}
{
"processor_class": "Wav2Vec2Processor"
}