语言: 迪维希语
数据集:

• 普通语音
  指标:
• 词错误率
  标签:
• 音频
• 自动语音识别
• 语音
  许可证: Apache-2.0

Wav2Vec2-Large-XLSR-53-迪维希语

基于facebook/wav2vec2-large-xlsr-53模型，使用普通语音的迪维希语数据进行了微调。
使用此模型时，请确保语音输入采样率为16kHz。

使用方法

该模型可直接使用（无需语言模型），如下所示：

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

test_dataset = load_dataset("common_voice", "dv", split="test[:2%]")  
processor = Wav2Vec2Processor.from_pretrained("shahukareem/wav2vec2-large-xlsr-53-dhivehi-v2")  
model = Wav2Vec2ForCTC.from_pretrained("shahukareem/wav2vec2-large-xlsr-53-dhivehi-v2")  

# 数据预处理  
# 需要将音频文件读取为数组  
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("预测结果:", processor.batch_decode(predicted_ids))  
print("参考文本:", test_dataset["sentence"][:2])  

评估

可以在普通语音的迪维希语测试数据上按如下方式评估模型：

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

test_dataset = load_dataset("common_voice", "dv", split="test")  
wer = load_metric("wer")  
processor = Wav2Vec2Processor.from_pretrained("shahukareem/wav2vec2-large-xlsr-53-dhivehi-v2")  
model = Wav2Vec2ForCTC.from_pretrained("shahukareem/wav2vec2-large-xlsr-53-dhivehi-v2")  
model.to("cuda")  

chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\،\.\؟\!\'\"\–\’]'  
resampler = torchaudio.transforms.Resample(48_000, 16_000)  

# 数据预处理  
# 需要将音频文件读取为数组  
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(speech_array).squeeze().numpy()  
    return batch  

test_dataset = test_dataset.map(speech_file_to_array_fn)  

# 评估函数  
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("词错误率: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))