Xlsr Indonesia

🚀 印度尼西亚语音识别模型评估项目

本项目专注于在印度尼西亚语的Common Voice数据集上进行语音识别模型的评估，利用Wav2Vec2ForCTC模型实现自动语音识别，为相关研究和应用提供了有效的评估方案。

🚀 快速开始

评估环境准备

在Common Voice印度尼西亚语测试集上进行评估，需要安装相关依赖库，以下是评估代码示例：

import torchaudio
from datasets import load_dataset, load_metric
from transformers import (
    Wav2Vec2ForCTC,
    Wav2Vec2Processor,
)
import torch
import re
import sys
model_name = "munggok/xlsr_indonesia"
device = "cuda"
chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"]'  # noqa: W605
model = Wav2Vec2ForCTC.from_pretrained(model_name).to(device)
processor = Wav2Vec2Processor.from_pretrained(model_name)
ds = load_dataset("common_voice", "id", split="test", data_dir="./cv-corpus-6.1-2020-12-11")
resampler = torchaudio.transforms.Resample(orig_freq=48_000, new_freq=16_000)

数据处理

对数据集进行处理，包括音频重采样和文本清理：

def map_to_array(batch):
    speech, _ = torchaudio.load(batch["path"])
    batch["speech"] = resampler.forward(speech.squeeze(0)).numpy()
    batch["sampling_rate"] = resampler.new_freq
    batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower().replace("’", "'")
    return batch
ds = ds.map(map_to_array)

模型预测

使用模型进行预测，并计算词错误率（WER）：

def map_to_pred(batch):
    features = processor(batch["speech"], sampling_rate=batch["sampling_rate"][0], padding=True, return_tensors="pt")
    input_values = features.input_values.to(device)
    attention_mask = features.attention_mask.to(device)
    with torch.no_grad():
        logits = model(input_values, attention_mask=attention_mask).logits
    pred_ids = torch.argmax(logits, dim=-1)
    batch["predicted"] = processor.batch_decode(pred_ids)
    batch["target"] = batch["sentence"]
    return batch
result = ds.map(map_to_pred, batched=True, batch_size=16, remove_columns=list(ds.features.keys()))
wer = load_metric("wer")
print(wer.compute(predictions=result["predicted"], references=result["target"]))

评估结果

结果：25.7 %

📦 项目信息