hubert-large-ls960-ft

import torch
from transformers import Wav2Vec2Processor, HubertForCTC
from datasets import load_dataset

processor = Wav2Vec2Processor.from_pretrained("facebook/hubert-large-ls960-ft")
model = HubertForCTC.from_pretrained("facebook/hubert-large-ls960-ft")
    
ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")

input_values = processor(ds[0]["audio"]["array"], return_tensors="pt").input_values  # Batch size 1
logits = model(input_values).logits
predicted_ids = torch.argmax(logits, dim=-1)
transcription = processor.decode(predicted_ids[0])

# ->"A MAN SAID TO THE UNIVERSE SIR I EXIST"