Wav2vec2 Large Xls Ar

🚀 Wav2Vec2-Large-XLSR-53-阿拉伯語模型

本模型基於Common Voice Corpus 5.1數據集，對阿拉伯語數據微調了facebook/wav2vec2-large-xlsr-53模型。使用此模型時，請確保輸入的語音採樣率為16kHz。

🚀 快速開始

本模型可直接使用（無需語言模型），使用方法如下：

💻 使用示例

基礎用法

import torch
import torchaudio
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
test_dataset = load_dataset("common_voice", "ar", split="test[:2%]")
processor = Wav2Vec2Processor.from_pretrained("mohamed1ai/wav2vec2-large-xls-ar")
model = Wav2Vec2ForCTC.from_pretrained("mohamed1ai/wav2vec2-large-xls-ar")
resampler = torchaudio.transforms.Resample(48_000, 16_000)
# Preprocessing the datasets.
# We need to read the aduio files as arrays
def speech_file_to_array_fn(batch):
    speech_array, sampling_rate = torchaudio.load(batch["path"])
    batch["speech"] = resampler(speech_array).squeeze().numpy()
    return 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():
     logits = 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])

高級用法

在阿拉伯語的Common Voice測試數據上，可按如下方式評估該模型：

import torch
import torchaudio
from datasets import load_dataset, load_metric
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import re
test_dataset = load_dataset("common_voice", "ar", split="test")
processor = Wav2Vec2Processor.from_pretrained("mohamed1ai/wav2vec2-large-xls-ar")
model = Wav2Vec2ForCTC.from_pretrained("mohamed1ai/wav2vec2-large-xls-ar")
model.to("cuda")
chars_to_ignore_regex = '[\,\؟\.\!\-\;\\:\'\"\☭\«\»\؛\—\ـ\_\،\“\%\‘\”\�]'
resampler = torchaudio.transforms.Resample(48_000, 16_000)
# Preprocessing the datasets.
# We need to read the aduio files as arrays
def speech_file_to_array_fn(batch):
    batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
    batch["sentence"] = re.sub('[a-z]','',batch["sentence"])
    batch["sentence"] = re.sub("[إأٱآا]", "ا", batch["sentence"])
    noise = re.compile(""" ّ    | # Tashdid
                             َ    | # Fatha
                             ً    | # Tanwin Fath
                             ُ    | # Damma
                             ٌ    | # Tanwin Damm
                             ِ    | # Kasra
                             ٍ    | # Tanwin Kasr
                             ْ    | # Sukun
                             ـ     # Tatwil/Kashida
                         """, re.VERBOSE)
    batch["sentence"] = re.sub(noise, '', batch["sentence"])
    speech_array, sampling_rate = torchaudio.load(batch["path"])
    batch["speech"] = resampler(speech_array).squeeze().numpy()
    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"), 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"])))

測試結果：52 %

📄 許可證

本模型使用的許可證為apache-2.0。

📦 模型信息