语言: sv 标签:

• 音频
• 自动语音识别
• 语音
• xlsr微调周 许可证: apache-2.0 模型索引:
• 名称: XLSR Wav2Vec2 威尔士语 by Srulik Ben David 结果:
  • 任务: 名称: 语音识别 类型: 自动语音识别 数据集: 名称: Common Voice cy 类型: common_voice 参数: cy
    指标:
    • 名称: 测试 WER 类型: wer 值: 29.4

Wav2Vec2-Large-XLSR-威尔士语 基于facebook/wav2vec2-large-xlsr-53在威尔士语Common Voice数据集上微调。 数据采用了标准增强方法进行处理。

使用此模型时，请确保语音输入采样率为16kHz。 测试结果: 29.4%

使用方法 该模型可直接使用（无需语言模型），如下所示：

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

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

processor = Wav2Vec2Processor.from_pretrained("Srulikbdd/Wav2vec2-large-xlsr-welsh")
model = Wav2Vec2ForCTC.from_pretrained("Srulikbdd/Wav2vec2-large-xlsr-welsh")

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

# 数据预处理
# 需要将音频文件读取为数组
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("预测结果:", processor.batch_decode(predicted_ids))
print("参考文本:", test_dataset["sentence"][:2])

评估 可通过以下方式在Common Voice威尔士语测试数据上评估模型：

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

test_dataset = load_dataset("common_voice", "cy", split="test") 

wer = load_metric("wer")

processor = Wav2Vec2Processor.from_pretrained("Srulikbdd/Wav2Vec2-large-xlsr-welsh")
model = Wav2Vec2ForCTC.from_pretrained("Srulikbdd/Wav2Vec2-large-xlsr-welsh")

model.to("cuda")

chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\u2013\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\u2014\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\%\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\]' 

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

# 数据预处理
# 需要将音频文件读取为数组
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)

# 评估函数
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"])))