python
import librosa
import torch
import torchaudio
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor


test_dataset = load_dataset("common_voice", "ka", split="test[:2%]") 

processor = Wav2Vec2Processor.from_pretrained("xsway/wav2vec2-large-xlsr-georgian")
model = Wav2Vec2ForCTC.from_pretrained("xsway/wav2vec2-large-xlsr-georgian") 

resampler = lambda sampling_rate, y: librosa.resample(y.numpy().squeeze(), sampling_rate, 16_000)

Preprocessing the datasets.
We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
\\\\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
\\\\tbatch["speech"] = resampler(sampling_rate, speech_array).squeeze()
\\\\treturn batch

test_dataset = test_dataset.map(speech_file_to_array_fn)
inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)

with torch.no_grad():
\\\\tlogits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits

predicted_ids = torch.argmax(logits, dim=-1)

print("Prediction:", processor.batch_decode(predicted_ids))
print("Reference:", test_dataset["sentence"][:2])

python
import torch
import torchaudio
from datasets import load_dataset, load_metric
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import re
import librosa

test_dataset = load_dataset("common_voice", "ka", split="test") 
wer = load_metric("wer")

processor = Wav2Vec2Processor.from_pretrained("xsway/wav2vec2-large-xlsr-georgian") 
model = Wav2Vec2ForCTC.from_pretrained("xsway/wav2vec2-large-xlsr-georgian") 
model.to("cuda")

chars_to_ignore_regex = '[\\\\\\\\,\\\\\\\\?\\\\\\\\.\\\\\\\\!\\\\\\\\-\\\\\\\\;\\\\\\\\:\\\\\\\\"\\\\\\\\“]' 
resampler = lambda sampling_rate, y: librosa.resample(y.numpy().squeeze(), sampling_rate, 16_000)

Preprocessing the datasets.
We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
  batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
  speech_array, sampling_rate = torchaudio.load(batch["path"])
  batch["speech"] = resampler(sampling_rate, speech_array).squeeze()
  return batch

test_dataset = test_dataset.map(speech_file_to_array_fn)

Preprocessing the datasets.
We need to read the audio files as arrays
def evaluate(batch):
  inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)

  with torch.no_grad():
    logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits

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

result = test_dataset.map(evaluate, batched=True, batch_size=8)

print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))