语言: el
数据集:

• common_voice
  指标:
• wer 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: Greek XLSR Wav2Vec2 Large 53 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 el 类型: common_voice 参数: el 指标: - 名称: 测试WER 类型: wer 值: 56.253154

Wav2Vec2-Large-XLSR-53-Greek

基于facebook/wav2vec2-large-xlsr-53在希腊语上使用Common Voice等数据集进行微调。使用该模型时，请确保语音输入采样率为16kHz。

使用方法

该模型可直接使用（无需语言模型）如下：

import torch
import torchaudio
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
test_dataset = load_dataset("common_voice", "el", split="test[:2%]")

processor = Wav2Vec2Processor.from_pretrained("skylord/greek_lsr_1") 
model = Wav2Vec2ForCTC.from_pretrained("skylord/greek_lsr_1") 

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

# 预处理数据集
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

该模型在Common Voice希腊语测试数据上的评估如下：

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

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

processor = Wav2Vec2Processor.from_pretrained("skylord/greek_lsr_1") 
model = Wav2Vec2ForCTC.from_pretrained("skylord/greek_lsr_1")
model.to("cuda")

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

# 预处理数据集
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)

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"])))

测试结果: 56.253154%

训练

训练使用了Common Voice的train、validation等数据集。训练脚本链接此处。