Wav2vec2 Large Xlsr 53 Dutch

🚀 荷兰语Wav2Vec2-Large-XLSR-53模型

本项目是基于 Common Voice 荷兰语数据集，对 facebook/wav2vec2-large-xlsr-53 模型进行微调后的语音识别模型。使用该模型时，请确保输入的语音采样率为16kHz。

🚀 快速开始

模型信息

模型评估

在Common Voice荷兰语测试数据上的评估结果显示，该模型的词错误率（WER）为17.09%。

训练数据

训练使用了Common Voice的 train 和 validation 数据集。

✨ 主要特性

• 基于大规模预训练模型 facebook/wav2vec2-large-xlsr-53 进行微调，在荷兰语语音识别任务上表现出色。
• 支持直接使用，无需语言模型。
• 提供了详细的使用示例和评估代码，方便用户快速上手。

💻 使用示例

基础用法

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

test_dataset = load_dataset("common_voice", "nl", split="test[:2%]")

processor = Wav2Vec2Processor.from_pretrained("wietsedv/wav2vec2-large-xlsr-53-dutch")
model = Wav2Vec2ForCTC.from_pretrained("wietsedv/wav2vec2-large-xlsr-53-dutch")

resampler = torchaudio.transforms.Resample(48_000, 16_000)

# Preprocessing the datasets.
# We need to read the aduio files as arrays
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("Prediction:", processor.batch_decode(predicted_ids))
print("Reference:", test_dataset["sentence"][:2])

高级用法

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

test_dataset = load_dataset("common_voice", "nl", split="test")
wer = load_metric("wer")

processor = Wav2Vec2Processor.from_pretrained("wietsedv/wav2vec2-large-xlsr-53-dutch")
model = Wav2Vec2ForCTC.from_pretrained("wietsedv/wav2vec2-large-xlsr-53-dutch")
model.to("cuda")

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

# Preprocessing the datasets.
# We need to read the aduio files as arrays
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)

# Preprocessing the datasets.
# We need to read the aduio files as arrays
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("WER: {:.2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))

📄 许可证

本项目采用Apache-2.0许可证。