japanese-hubert-base

import soundfile as sf
from transformers import AutoFeatureExtractor, AutoModel

model_name = "rinna/japanese-hubert-base"
feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name)
model.eval()

raw_speech_16kHz, sr = sf.read(audio_file)
inputs = feature_extractor(
    raw_speech_16kHz,
    return_tensors="pt",
    sampling_rate=sr,
)
outputs = model(**inputs)

print(f"Input:  {inputs.input_values.size()}")  # [1, #samples]
print(f"Output: {outputs.last_hidden_state.size()}")  # [1, #frames, 768]