lm.py

from transformers import Wav2Vec2ProcessorWithLM
import torchaudio

import torch
from datasets import load_dataset
from transformers import AutoModelForCTC, AutoProcessor
import torchaudio.functional as F

# processor = Wav2Vec2ProcessorWithLM.from_pretrained(".")

model_id = "."


sample_iter = iter(load_dataset("mozilla-foundation/common_voice_7_0", "sv-SE", split="test", streaming=True, use_auth_token=True))

sample = next(sample_iter)
resampled_audio = F.resample(torch.tensor(sample["audio"]["array"]), 48_000, 16_000).numpy()

model = AutoModelForCTC.from_pretrained(model_id)
processor = AutoProcessor.from_pretrained(model_id)

input_values = processor(resampled_audio, return_tensors="pt").input_values

with torch.no_grad():
    logits = model(input_values).logits
    transcription = processor.batch_decode(logits.numpy()).text
    print(transcription)