S2T2-Wav2Vec2-CoVoST2-EN-DE-ST

s2t-wav2vec2-large-en-de是一个专为端到端语音翻译（ST）训练的语音到文本Transformer模型。S2T2模型在某某论文中提出，并在某某时正式发布。

模型描述

S2T2是一个基于Transformer的序列到序列（语音编码器-解码器）模型，旨在进行端到端的自动语音识别（ASR）和语音翻译（ST）。它使用预训练的某某作为编码器和基于Transformer的解码器。该模型使用标准的自回归交叉熵损失进行训练，并自动逐步生成翻译。

预期用途和限制

该模型可以用于将英语语音转换为德语文本的端到端翻译。请查看某某寻找其他S2T2检查点。

如何使用

由于这是一个标准的序列到序列Transformer模型，您可以使用generate方法通过将语音特征传递给模型来生成转录。

您可以通过ASR管道直接使用模型

from datasets import load_dataset
from transformers import pipeline

librispeech_en = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
asr = pipeline("automatic-speech-recognition", model="facebook/s2t-wav2vec2-large-en-de", feature_extractor="facebook/s2t-wav2vec2-large-en-de")

translation_de = asr(librispeech_en[0]["file"])

或按照以下步骤逐步使用：

import torch
from transformers import Speech2Text2Processor, SpeechEncoderDecoder
from datasets import load_dataset

import soundfile as sf
model = SpeechEncoderDecoder.from_pretrained("facebook/s2t-wav2vec2-large-en-de")
processor = Speech2Text2Processor.from_pretrained("facebook/s2t-wav2vec2-large-en-de")

def map_to_array(batch):
    speech, _ = sf.read(batch["file"])
    batch["speech"] = speech
    return batch
    
ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
ds = ds.map(map_to_array)

inputs = processor(ds["speech"][0], sampling_rate=16_000, return_tensors="pt")
generated_ids = model.generate(input_ids=inputs["input_features"], attention_mask=inputs["attention_mask"])
transcription = processor.batch_decode(generated_ids)

评估结果

en-de的CoVoST-V2测试结果（BLEU分数）：26.5

获取更多信息，请参阅某某，特别是表2的第10行。

BibTeX条目和引用信息

@article{DBLP:journals/corr/abs-2104-06678,
  author    = {Changhan Wang and
               Anne Wu and
               Juan Miguel Pino and
               Alexei Baevski and
               Michael Auli and
               Alexis Conneau},
  title     = {Large-Scale Self- and Semi-Supervised Learning for Speech Translation},
  journal   = {CoRR},
  volume    = {abs/2104.06678},
  year      = {2021},
  url       = {https://arxiv.org/abs/2104.06678},
  archivePrefix = {arXiv},
  eprint    = {2104.06678},
  timestamp = {Thu, 12 Aug 2021 15:37:06 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2104-06678.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}