Wav2Vec2-Base-Vietnamese-270h

在包含来自多个数据集的约270小时标记数据的基础上，对越南语言识别任务进行了Wav2Vec2模型的微调，其中包括 Common Voice 、 VIVOS 和 VLSP2020 。该模型使用SpeechBrain工具包进行了微调，并使用了自定义的分词器。为了获得更好的体验，我们鼓励您了解一下 SpeechBrain 。在使用此模型时，请确保语音输入采样频率为16kHz。有关如何在特定语言上微调Wav2Vec2模型的方法，请参阅 huggingface blog 或 speechbrain 。

基准词错误率结果：

该语言模型使用 OSCAR 数据集进行了训练，训练文本大小约为32GB。

安装SpeechBrain

要使用该模型，您应安装speechbrain > 0.5.10

用法

可以直接使用该模型（无需语言模型），如下所示：

from speechbrain.pretrained import EncoderASR

model = EncoderASR.from_hparams(source="dragonSwing/wav2vec2-base-vn-270h", savedir="pretrained_models/asr-wav2vec2-vi")
model.transcribe_file('dragonSwing/wav2vec2-base-vn-270h/example.mp3')
# Output: được hồ chí minh coi là một động lực lớn của sự phát triển đất nước

在GPU上的推理

要在GPU上执行推理，请在调用from_hparams方法时添加run_opts={"device":"cuda"}

评估

可以如下所示对Common Voice 8.0的越南语测试数据进行评估。

import torch
import torchaudio
from datasets import load_dataset, load_metric, Audio
from transformers import Wav2Vec2FeatureExtractor
from speechbrain.pretrained import EncoderASR
import re
test_dataset = load_dataset("mozilla-foundation/common_voice_8_0", "vi", split="test", use_auth_token=True)
test_dataset = test_dataset.cast_column("audio", Audio(sampling_rate=16_000))
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
wer = load_metric("wer")
extractor = Wav2Vec2FeatureExtractor.from_pretrained("dragonSwing/wav2vec2-base-vn-270h")
model = EncoderASR.from_hparams(source="dragonSwing/wav2vec2-base-vn-270h", savedir="pretrained_models/asr-wav2vec2-vi", run_opts={'device': device})
chars_to_ignore_regex = r'[,?.!\-;:"“%\'�]'
# Preprocessing the datasets.
# We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
  audio = batch["audio"]
  batch["target_text"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
  batch['speech'] = audio['array']
  return batch
test_dataset = test_dataset.map(speech_file_to_array_fn)

def evaluate(batch):
  # For padding inputs only
  inputs = extractor(
    batch['speech'], 
    sampling_rate=16000, 
    return_tensors="pt", 
    padding=True, 
    do_normalize=False
  ).input_values
  input_lens = torch.ones(inputs.shape[0])
  pred_str, pred_tokens = model.transcribe_batch(inputs, input_lens)
  batch["pred_strings"] = pred_str
  
  return batch
result = test_dataset.map(evaluate, batched=True, batch_size=1)
print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["target_text"])))

测试结果：12.155553%

@misc{SB2021,
    author = {Ravanelli, Mirco and Parcollet, Titouan and Rouhe, Aku and Plantinga, Peter and Rastorgueva, Elena and Lugosch, Loren and Dawalatabad, Nauman and Ju-Chieh, Chou and Heba, Abdel and Grondin, Francois and Aris, William and Liao, Chien-Feng and Cornell, Samuele and Yeh, Sung-Lin and Na, Hwidong and Gao, Yan and Fu, Szu-Wei and Subakan, Cem and De Mori, Renato and Bengio, Yoshua },
    title = {SpeechBrain},
    year = {2021},
    publisher = {GitHub},
    journal = {GitHub repository},
    howpublished = {\\\\url{https://github.com/speechbrain/speechbrain}},
  }

SpeechBrain是一个开源的一体化语音工具包。它设计简单、极其灵活和用户友好。在各个领域取得了有竞争力或达到最新技术水平的性能。网站： https://speechbrain.github.io GitHub： https://github.com/speechbrain/speechbrain