Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
mms
xlsr
Inference Endpoints
mms-zeroshot-300m / preprocessor_config.json
Vineel Pratap
model_upload
feacb2c
raw
history blame contribute delete
254 Bytes
{
"do_normalize": true,
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
"feature_size": 1,
"padding_side": "right",
"padding_value": 0,
"processor_class": "Wav2Vec2Processor",
"return_attention_mask": true,
"sampling_rate": 16000
}