SakshiRathi77/wav2vec2_xlsr_300m

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


test_dataset = load_dataset("mozilla-foundation/common_voice_8_0", "hi", split="test")
wer = load_metric("wer")
cer = load_metric("cer")

processor = Wav2Vec2Processor.from_pretrained("SakshiRathi77/wav2vec2_xlsr_300m")
model = Wav2Vec2ForCTC.from_pretrained("SakshiRathi77/wav2vec2_xlsr_300m")
model.to("cuda")


# Preprocessing the datasets.
def speech_file_to_array_fn(batch):
    chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\’\'\|\&\–]'
    remove_en = '[A-Za-z]'
    batch["sentence"] = re.sub(chars_to_ignore_regex, "", batch["sentence"].lower())
    batch["sentence"] = re.sub(remove_en, "", batch["sentence"]).lower()
    batch["sentence"] = unicodedata.normalize("NFKC", batch["sentence"])

    speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
    batch["speech"] = speech_array
    return batch

test_dataset = test_dataset.map(speech_file_to_array_fn)

# Preprocessing the datasets.
# We need to read the aduio 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")).logits

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

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

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

WER: 52.09850206372026
CER: 17.902923538230883