注意

单击此处下载完整的示例代码

多语言数据的强制对齐¶

本教程介绍如何将非英语语言的转录与语音对齐。

对齐非英语（标准化）成绩单的过程与对齐英语（标准化）成绩单，英语的过程在 CTC 强制对齐教程中详细介绍。在本教程中，我们使用 TorchAudio 的高级 API ，它将预训练的 model、tokenizer 和 aligner 来执行强制对齐，以更少的代码执行强制对齐。

import torch
import torchaudio

print(torch.__version__)
print(torchaudio.__version__)

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)

2.4.0
2.4.0
cuda

from typing import List

import IPython
import matplotlib.pyplot as plt

创建管道¶

首先，我们实例化模型和前/后处理管道。

下图说明了对齐过程。

https://download.pytorch.org/torchaudio/doc-assets/pipelines-wav2vec2fabundle.png

波形被传递给声学模型，该模型生成代币的概率分布。转录文本将传递给 tokenizer，后者将转录文本转换为标记序列。 Aligner 从声学模型和分词器中获取结果并生成每个令牌的时间戳。

注意

此过程期望输入转录已规范化。规范化过程，涉及非英语的罗马化 languages 与语言相关，因此本教程不涉及但我们会仔细研究它。

声学模型和分词器必须使用同一组令牌。为了便于创建匹配的处理器，将预先训练的声学模型和分词器。就是这样一个例子。

以下代码实例化了一个预先训练的声学模型，即 tokenizer 它使用与模型相同的 tokens 集和 aligner。

from torchaudio.pipelines import MMS_FA as bundle

model = bundle.get_model()
model.to(device)

tokenizer = bundle.get_tokenizer()
aligner = bundle.get_aligner()

注意

默认情况下，由 'method 实例化的模型包括 token 的特征维度。您可以通过传递 .<star>with_star=False

的声学模型是作为研究项目 Scaling Speech Technology to 1,000+ Languages 的一部分创建并开源。它使用来自 1100+ 种语言的 23,000 小时音频进行了训练。

分词器只是将规范化字符映射到整数。您可以按如下方式检查映射;

print(bundle.get_dict())

{'-': 0, 'a': 1, 'i': 2, 'e': 3, 'n': 4, 'o': 5, 'u': 6, 't': 7, 's': 8, 'r': 9, 'm': 10, 'k': 11, 'l': 12, 'd': 13, 'g': 14, 'h': 15, 'y': 16, 'b': 17, 'p': 18, 'w': 19, 'c': 20, 'v': 21, 'j': 22, 'z': 23, 'f': 24, "'": 25, 'q': 26, 'x': 27, '*': 28}

矫正器在内部使用和来推断时间 Stamp 的标记。

底层机制的详细信息在 CTC 强制对齐 API 教程中介绍，所以请参考它。

我们定义了一个实用程序函数，该函数执行强制对齐上述模型，tokenizer 和 aligner。

def compute_alignments(waveform: torch.Tensor, transcript: List[str]):
    with torch.inference_mode():
        emission, _ = model(waveform.to(device))
        token_spans = aligner(emission[0], tokenizer(transcript))
    return emission, token_spans

我们还定义了用于绘制结果和预览的实用函数音频片段。

# Compute average score weighted by the span length
def _score(spans):
    return sum(s.score * len(s) for s in spans) / sum(len(s) for s in spans)


def plot_alignments(waveform, token_spans, emission, transcript, sample_rate=bundle.sample_rate):
    ratio = waveform.size(1) / emission.size(1) / sample_rate

    fig, axes = plt.subplots(2, 1)
    axes[0].imshow(emission[0].detach().cpu().T, aspect="auto")
    axes[0].set_title("Emission")
    axes[0].set_xticks([])

    axes[1].specgram(waveform[0], Fs=sample_rate)
    for t_spans, chars in zip(token_spans, transcript):
        t0, t1 = t_spans[0].start, t_spans[-1].end
        axes[0].axvspan(t0 - 0.5, t1 - 0.5, facecolor="None", hatch="/", edgecolor="white")
        axes[1].axvspan(ratio * t0, ratio * t1, facecolor="None", hatch="/", edgecolor="white")
        axes[1].annotate(f"{_score(t_spans):.2f}", (ratio * t0, sample_rate * 0.51), annotation_clip=False)

        for span, char in zip(t_spans, chars):
            t0 = span.start * ratio
            axes[1].annotate(char, (t0, sample_rate * 0.55), annotation_clip=False)

    axes[1].set_xlabel("time [second]")
    fig.tight_layout()

def preview_word(waveform, spans, num_frames, transcript, sample_rate=bundle.sample_rate):
    ratio = waveform.size(1) / num_frames
    x0 = int(ratio * spans[0].start)
    x1 = int(ratio * spans[-1].end)
    print(f"{transcript} ({_score(spans):.2f}): {x0 / sample_rate:.3f} - {x1 / sample_rate:.3f} sec")
    segment = waveform[:, x0:x1]
    return IPython.display.Audio(segment.numpy(), rate=sample_rate)

规范化转录本¶

必须事先对传递给管道的转录文本进行规范化。规范化的确切过程取决于语言。

没有明确单词边界的语言（如中文、日语和韩语）需要首先进行分段。有专门的工具可以做到这一点，但假设我们已经进行了分段抄本。

规范化的第一步是罗马化。Uroman 是一种工具支持多种语言。

这是一个 BASH 命令，用于将输入文本文件罗马化并写入使用 .uroman

$ echo "des événements d'actualité qui se sont produits durant l'année 1882" > text.txt
$ uroman/bin/uroman.pl < text.txt > text_romanized.txt
$ cat text_romanized.txt

Cette page concerne des evenements d'actualite qui se sont produits durant l'annee 1882

下一步是删除非字母和标点符号。以下代码片段对罗马化的转录文本进行了规范化。

import re


def normalize_uroman(text):
    text = text.lower()
    text = text.replace("’", "'")
    text = re.sub("([^a-z' ])", " ", text)
    text = re.sub(' +', ' ', text)
    return text.strip()


with open("text_romanized.txt", "r") as f:
    for line in f:
        text_normalized = normalize_uroman(line)
        print(text_normalized)

在上述示例上运行脚本将生成以下内容。

cette page concerne des evenements d'actualite qui se sont produits durant l'annee

请注意，在此示例中，由于 “1882” 不是用罗马音化的，它在 normalization 步骤中删除。为避免这种情况，需要将数字罗马化，但众所周知，这是一项非同艰的任务。uroman

将转录与语音对齐¶

现在，我们对多种语言执行强制对齐。

德语¶

text_raw = "aber seit ich bei ihnen das brot hole"
text_normalized = "aber seit ich bei ihnen das brot hole"

url = "https://download.pytorch.org/torchaudio/tutorial-assets/10349_8674_000087.flac"
waveform, sample_rate = torchaudio.load(
    url, frame_offset=int(0.5 * bundle.sample_rate), num_frames=int(2.5 * bundle.sample_rate)
)

assert sample_rate == bundle.sample_rate

transcript = text_normalized.split()
tokens = tokenizer(transcript)

emission, token_spans = compute_alignments(waveform, transcript)
num_frames = emission.size(1)

plot_alignments(waveform, token_spans, emission, transcript)

print("Raw Transcript: ", text_raw)
print("Normalized Transcript: ", text_normalized)
IPython.display.Audio(waveform, rate=sample_rate)

Raw Transcript:  aber seit ich bei ihnen das brot hole
Normalized Transcript:  aber seit ich bei ihnen das brot hole

preview_word(waveform, token_spans[0], num_frames, transcript[0])

aber (0.96): 0.222 - 0.464 sec

preview_word(waveform, token_spans[1], num_frames, transcript[1])

seit (0.78): 0.565 - 0.766 sec

preview_word(waveform, token_spans[2], num_frames, transcript[2])

ich (0.91): 0.847 - 0.948 sec

preview_word(waveform, token_spans[3], num_frames, transcript[3])

bei (0.96): 1.028 - 1.190 sec

preview_word(waveform, token_spans[4], num_frames, transcript[4])

ihnen (0.65): 1.331 - 1.532 sec

preview_word(waveform, token_spans[5], num_frames, transcript[5])

das (0.54): 1.573 - 1.774 sec

preview_word(waveform, token_spans[6], num_frames, transcript[6])

brot (0.86): 1.855 - 2.117 sec

preview_word(waveform, token_spans[7], num_frames, transcript[7])

hole (0.71): 2.177 - 2.480 sec

中文¶

中文是一种基于字符的语言，没有明确的词级原始书面形式的分词化（用空格分隔）。为了获取单词级别对齐，您需要首先对成绩单进行分词在单词级别使用单词分词器，例如“Stanford Tokenizer 的 Tokenizer”。但是，如果您只想要字符级对齐，则不需要这样做。

text_raw = "关 服务 高端 产品 仍 处于 供不应求 的 局面"
text_normalized = "guan fuwu gaoduan chanpin reng chuyu gongbuyingqiu de jumian"

url = "https://download.pytorch.org/torchaudio/tutorial-assets/mvdr/clean_speech.wav"
waveform, sample_rate = torchaudio.load(url)
waveform = waveform[0:1]

assert sample_rate == bundle.sample_rate

transcript = text_normalized.split()
emission, token_spans = compute_alignments(waveform, transcript)
num_frames = emission.size(1)

plot_alignments(waveform, token_spans, emission, transcript)

print("Raw Transcript: ", text_raw)
print("Normalized Transcript: ", text_normalized)
IPython.display.Audio(waveform, rate=sample_rate)

Raw Transcript:  关 服务 高端 产品 仍 处于 供不应求 的 局面
Normalized Transcript:  guan fuwu gaoduan chanpin reng chuyu gongbuyingqiu de jumian

preview_word(waveform, token_spans[0], num_frames, transcript[0])

guan (0.33): 0.020 - 0.141 sec

preview_word(waveform, token_spans[1], num_frames, transcript[1])

fuwu (0.31): 0.221 - 0.583 sec

preview_word(waveform, token_spans[2], num_frames, transcript[2])

gaoduan (0.74): 0.724 - 1.065 sec

preview_word(waveform, token_spans[3], num_frames, transcript[3])

chanpin (0.73): 1.126 - 1.528 sec

preview_word(waveform, token_spans[4], num_frames, transcript[4])

reng (0.86): 1.608 - 1.809 sec

preview_word(waveform, token_spans[5], num_frames, transcript[5])

chuyu (0.80): 1.849 - 2.151 sec

preview_word(waveform, token_spans[6], num_frames, transcript[6])

gongbuyingqiu (0.93): 2.251 - 2.894 sec

preview_word(waveform, token_spans[7], num_frames, transcript[7])

de (0.98): 2.935 - 3.015 sec

preview_word(waveform, token_spans[8], num_frames, transcript[8])

jumian (0.95): 3.075 - 3.477 sec

波兰语¶

text_raw = "wtedy ujrzałem na jego brzuchu okrągłą czarną ranę"
text_normalized = "wtedy ujrzalem na jego brzuchu okragla czarna rane"

url = "https://download.pytorch.org/torchaudio/tutorial-assets/5090_1447_000088.flac"
waveform, sample_rate = torchaudio.load(url, num_frames=int(4.5 * bundle.sample_rate))

assert sample_rate == bundle.sample_rate

transcript = text_normalized.split()
emission, token_spans = compute_alignments(waveform, transcript)
num_frames = emission.size(1)

plot_alignments(waveform, token_spans, emission, transcript)

print("Raw Transcript: ", text_raw)
print("Normalized Transcript: ", text_normalized)
IPython.display.Audio(waveform, rate=sample_rate)

Raw Transcript:  wtedy ujrzałem na jego brzuchu okrągłą czarną ranę
Normalized Transcript:  wtedy ujrzalem na jego brzuchu okragla czarna rane

preview_word(waveform, token_spans[0], num_frames, transcript[0])

wtedy (1.00): 0.783 - 1.145 sec

preview_word(waveform, token_spans[1], num_frames, transcript[1])

ujrzalem (0.96): 1.286 - 1.788 sec

preview_word(waveform, token_spans[2], num_frames, transcript[2])

na (1.00): 1.868 - 1.949 sec

preview_word(waveform, token_spans[3], num_frames, transcript[3])

jego (1.00): 2.009 - 2.230 sec

preview_word(waveform, token_spans[4], num_frames, transcript[4])

brzuchu (0.97): 2.330 - 2.732 sec

preview_word(waveform, token_spans[5], num_frames, transcript[5])

okragla (1.00): 2.893 - 3.415 sec

preview_word(waveform, token_spans[6], num_frames, transcript[6])

czarna (0.90): 3.556 - 3.938 sec

preview_word(waveform, token_spans[7], num_frames, transcript[7])

rane (1.00): 4.098 - 4.399 sec

葡萄牙语¶

text_raw = "na imensa extensão onde se esconde o inconsciente imortal"
text_normalized = "na imensa extensao onde se esconde o inconsciente imortal"

url = "https://download.pytorch.org/torchaudio/tutorial-assets/6566_5323_000027.flac"
waveform, sample_rate = torchaudio.load(
    url, frame_offset=int(bundle.sample_rate), num_frames=int(4.6 * bundle.sample_rate)
)

assert sample_rate == bundle.sample_rate

transcript = text_normalized.split()
emission, token_spans = compute_alignments(waveform, transcript)
num_frames = emission.size(1)

plot_alignments(waveform, token_spans, emission, transcript)

print("Raw Transcript: ", text_raw)
print("Normalized Transcript: ", text_normalized)
IPython.display.Audio(waveform, rate=sample_rate)

Raw Transcript:  na imensa extensão onde se esconde o inconsciente imortal
Normalized Transcript:  na imensa extensao onde se esconde o inconsciente imortal

preview_word(waveform, token_spans[0], num_frames, transcript[0])

na (1.00): 0.020 - 0.080 sec

preview_word(waveform, token_spans[1], num_frames, transcript[1])

imensa (0.90): 0.120 - 0.502 sec

preview_word(waveform, token_spans[2], num_frames, transcript[2])

extensao (0.92): 0.542 - 1.205 sec

preview_word(waveform, token_spans[3], num_frames, transcript[3])

onde (1.00): 1.446 - 1.667 sec

preview_word(waveform, token_spans[4], num_frames, transcript[4])

se (0.99): 1.748 - 1.828 sec

preview_word(waveform, token_spans[5], num_frames, transcript[5])

esconde (0.99): 1.888 - 2.591 sec

preview_word(waveform, token_spans[6], num_frames, transcript[6])

o (0.98): 2.852 - 2.872 sec

preview_word(waveform, token_spans[7], num_frames, transcript[7])

inconsciente (0.80): 2.933 - 3.897 sec

preview_word(waveform, token_spans[8], num_frames, transcript[8])

imortal (0.86): 3.937 - 4.560 sec

意大利语¶

text_raw = "elle giacean per terra tutte quante"
text_normalized = "elle giacean per terra tutte quante"

url = "https://download.pytorch.org/torchaudio/tutorial-assets/642_529_000025.flac"
waveform, sample_rate = torchaudio.load(url, num_frames=int(4 * bundle.sample_rate))

assert sample_rate == bundle.sample_rate

transcript = text_normalized.split()
emission, token_spans = compute_alignments(waveform, transcript)
num_frames = emission.size(1)

plot_alignments(waveform, token_spans, emission, transcript)

print("Raw Transcript: ", text_raw)
print("Normalized Transcript: ", text_normalized)
IPython.display.Audio(waveform, rate=sample_rate)

Raw Transcript:  elle giacean per terra tutte quante
Normalized Transcript:  elle giacean per terra tutte quante

preview_word(waveform, token_spans[0], num_frames, transcript[0])

elle (1.00): 0.563 - 0.864 sec

preview_word(waveform, token_spans[1], num_frames, transcript[1])

giacean (0.99): 0.945 - 1.467 sec

preview_word(waveform, token_spans[2], num_frames, transcript[2])

per (1.00): 1.588 - 1.789 sec

preview_word(waveform, token_spans[3], num_frames, transcript[3])

terra (1.00): 1.950 - 2.392 sec

preview_word(waveform, token_spans[4], num_frames, transcript[4])

tutte (1.00): 2.533 - 2.975 sec

preview_word(waveform, token_spans[5], num_frames, transcript[5])

quante (1.00): 3.055 - 3.678 sec

结论¶

在本教程中，我们了解了如何使用 torchaudio 的强制对齐 API 和 Wav2Vec2 预先训练的多语言声学模型进行对齐语音数据转换为五种语言的转录内容。

确认¶

感谢 Vineel Pratap 和 Zhaoheng Ni 用于开发和开源强制对准器 API。

脚本总运行时间：（0 分 4.092 秒）

由 Sphinx-Gallery 生成的图库