wav2vec2-conformer-rope-large-960h-ft

 from transformers import Wav2Vec2Processor, Wav2Vec2ConformerForCTC
 from datasets import load_dataset
 import torch
 
 # load model and processor
 processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-conformer-rope-large-960h-ft")
 model = Wav2Vec2ConformerForCTC.from_pretrained("facebook/wav2vec2-conformer-rope-large-960h-ft")
     
 # load dummy dataset and read soundfiles
 ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
 
 # tokenize
 input_values = processor(ds[0]["audio"]["array"], return_tensors="pt", padding="longest").input_values
 
 # retrieve logits
 logits = model(input_values).logits
 
 # take argmax and decode
 predicted_ids = torch.argmax(logits, dim=-1)
 transcription = processor.batch_decode(predicted_ids)

from datasets import load_dataset
from transformers import Wav2Vec2ConformerForCTC, Wav2Vec2Processor
import torch
from jiwer import wer


librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")

model = Wav2Vec2ConformerForCTC.from_pretrained("facebook/wav2vec2-conformer-rope-large-960h-ft").to("cuda")
processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-conformer-rope-large-960h-ft")

def map_to_pred(batch):
    inputs = processor(batch["audio"]["array"], return_tensors="pt", padding="longest")
    input_values = inputs.input_values.to("cuda")
    attention_mask = inputs.attention_mask.to("cuda")
    
    with torch.no_grad():
        logits = model(input_values, attention_mask=attention_mask).logits

    predicted_ids = torch.argmax(logits, dim=-1)
    transcription = processor.batch_decode(predicted_ids)
    batch["transcription"] = transcription
    return batch

result = librispeech_eval.map(map_to_pred, remove_columns=["audio"])

print("WER:", wer(result["text"], result["transcription"]))