from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
from datasets import load_dataset
import torch

# load model and processor
processor = Wav2Vec2Processor.from_pretrained("GetmanY1/wav2vec2-xlarge-fi-150k-finetuned")
model = Wav2Vec2ForCTC.from_pretrained("GetmanY1/wav2vec2-xlarge-fi-150k-finetuned")

# load dummy dataset and read soundfiles
ds = load_dataset("mozilla-foundation/common_voice_16_1", "fi", split='test')

# tokenize
input_values = processor(ds[0]["audio"]["array"], return_tensors="pt", padding="longest").input_values  # Batch size 1

# retrieve logits
logits = model(input_values).logits

# take argmax and decode
predicted_ids = torch.argmax(logits, dim=-1)
transcription = processor.batch_decode(predicted_ids)