🚀 Wav2Vec2-Large-XLSR-53-阿拉伯语模型
本模型基于Common Voice Corpus 5.1数据集,对阿拉伯语数据微调了facebook/wav2vec2-large-xlsr-53模型。使用此模型时,请确保输入的语音采样率为16kHz。
🚀 快速开始
本模型可直接使用(无需语言模型),使用方法如下:
💻 使用示例
基础用法
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)
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])
高级用法
在阿拉伯语的Common Voice测试数据上,可按如下方式评估该模型:
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)
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)
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"])))
测试结果:52 %
📄 许可证
本模型使用的许可证为apache-2.0
。
📦 模型信息
属性 |
详情 |
模型类型 |
微调后的Wav2Vec2-Large-XLSR-53阿拉伯语模型 |
训练数据 |
Common Voice Corpus 5.1阿拉伯语数据集 |
评估指标 |
词错误率(WER) |
任务类型 |
自动语音识别 |
测试集WER |
52% |