模型:

superb/wav2vec2-base-superb-ic

英文

Wav2Vec2-Base用于意图分类

模型描述

这是 S3PRL's Wav2Vec2 for the SUPERB Intent Classification task 的一个移植版本。

基础模型是 wav2vec2-base ,它是在16kHz采样的语音音频上进行预训练的。使用该模型时,请确保您的语音输入也是以16kHz采样的。

有关更多信息,请参阅 SUPERB: Speech processing Universal PERformance Benchmark

任务和数据集描述

意图分类(IC)将话语划分为预定义的类别,以确定说话人的意图。SUPERB使用了 Fluent Speech Commands 数据集,其中每个话语都标有三个意图标签:行动(action)、对象(object)和位置(location)。

有关原始模型的训练和评估说明,请参阅 S3PRL downstream task README

使用示例

您可以直接使用模型,如下所示:

import torch
import librosa
from datasets import load_dataset
from transformers import Wav2Vec2ForSequenceClassification, Wav2Vec2FeatureExtractor

def map_to_array(example):
    speech, _ = librosa.load(example["file"], sr=16000, mono=True)
    example["speech"] = speech
    return example

# load a demo dataset and read audio files
dataset = load_dataset("anton-l/superb_demo", "ic", split="test")
dataset = dataset.map(map_to_array)

model = Wav2Vec2ForSequenceClassification.from_pretrained("superb/wav2vec2-base-superb-ic")
feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained("superb/wav2vec2-base-superb-ic")

# compute attention masks and normalize the waveform if needed
inputs = feature_extractor(dataset[:4]["speech"], sampling_rate=16000, padding=True, return_tensors="pt")

logits = model(**inputs).logits

action_ids = torch.argmax(logits[:, :6], dim=-1).tolist()
action_labels = [model.config.id2label[_id] for _id in action_ids]

object_ids = torch.argmax(logits[:, 6:20], dim=-1).tolist()
object_labels = [model.config.id2label[_id + 6] for _id in object_ids]

location_ids = torch.argmax(logits[:, 20:24], dim=-1).tolist()
location_labels = [model.config.id2label[_id + 20] for _id in location_ids]

评估结果

评估指标是准确度。

s3prl transformers
test 0.9235 N/A

BibTeX条目和引文信息

@article{yang2021superb,
  title={SUPERB: Speech processing Universal PERformance Benchmark},
  author={Yang, Shu-wen and Chi, Po-Han and Chuang, Yung-Sung and Lai, Cheng-I Jeff and Lakhotia, Kushal and Lin, Yist Y and Liu, Andy T and Shi, Jiatong and Chang, Xuankai and Lin, Guan-Ting and others},
  journal={arXiv preprint arXiv:2105.01051},
  year={2021}
}