Feature Extraction
Transformers
PyTorch
Safetensors
Japanese
hubert
speech
japanese-hubert-large / preprocessor_config.json
yky-h's picture
Add model
29f8087
raw
history blame
214 Bytes
{
"do_normalize": true,
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
"feature_size": 1,
"padding_side": "right",
"padding_value": 0.0,
"return_attention_mask": true,
"sampling_rate": 16000
}