from datasets import load_dataset,load_metric,Audio
from transformers import WhisperForConditionalGeneration, WhisperProcessor
import torch
import torchaudio

test_dataset = load_dataset("mozilla-foundation/common_voice_13_0", "hi", split="test")
wer = load_metric("wer")
cer = load_metric("cer")

processor = WhisperProcessor.from_pretrained("kingabzpro/whisper-small-hi-cv")
model = WhisperForConditionalGeneration.from_pretrained("kingabzpro/whisper-small-hi-cv").to("cuda")
test_dataset = test_dataset.cast_column("audio", Audio(sampling_rate=16000))

def map_to_pred(batch):
    audio = batch["audio"]
    input_features = processor(audio["array"], sampling_rate=audio["sampling_rate"], return_tensors="pt").input_features
    batch["reference"] = processor.tokenizer._normalize(batch['sentence'])

    with torch.no_grad():
        predicted_ids = model.generate(input_features.to("cuda"))[0]
    transcription = processor.decode(predicted_ids)
    batch["prediction"] = processor.tokenizer._normalize(transcription)
    return batch

result = test_dataset.map(map_to_pred)

print("WER: {:2f}".format(100 * wer.compute(predictions=result["prediction"], references=result["reference"])))
print("CER: {:2f}".format(100 * cer.compute(predictions=result["prediction"], references=result["reference"])))

bash

WER: 23.3824
CER: 10.5288