Wav2vec2 Large Xlsr Turkish Artificial

🚀 Wav2Vec2-Large-XLSR-土耳其語模型

該模型基於 facebook/wav2vec2-large-xlsr-53 在 土耳其人工通用語音數據集 上進行微調。使用此模型時，請確保語音輸入的採樣率為 16kHz。

模型信息

模型評估結果

• 模型名稱：XLSR Wav2Vec2 Turkish with Artificial Voices by Cahya
• 任務：語音識別（自動語音識別類型）
• 數據集：Common Voice tr（通用語音土耳其語數據集）
• 評估指標：測試集詞錯誤率（WER）為 66.98

🚀 快速開始

使用此模型前，請確保語音輸入的採樣率為 16kHz。

💻 使用示例

基礎用法

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

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

processor = Wav2Vec2Processor.from_pretrained("cahya/wav2vec2-large-xlsr-turkish-artificial")
model = Wav2Vec2ForCTC.from_pretrained("cahya/wav2vec2-large-xlsr-turkish-artificial")


# 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"])
  resampler = torchaudio.transforms.Resample(sampling_rate, 16_000)
  batch["speech"] = resampler(speech_array).squeeze().numpy()
  return batch

test_dataset = test_dataset.map(speech_file_to_array_fn)
inputs = processor(test_dataset[:2]["speech"], 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[:2]["sentence"])

高級用法

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

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

processor = Wav2Vec2Processor.from_pretrained("cahya/wav2vec2-large-xlsr-turkish-artificial")
model = Wav2Vec2ForCTC.from_pretrained("cahya/wav2vec2-large-xlsr-turkish-artificial") 
model.to("cuda")

chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\‘\”\'\`…\’»«]'

# 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"])
  resampler = torchaudio.transforms.Resample(sampling_rate, 16_000)
  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"])))

測試結果：66.98 %

📚 詳細文檔

訓練信息

使用人工通用語音數據集的 train 和 validation 子集對模型進行微調。訓練腳本可在 此處 找到。

📄 許可證

本模型使用 Apache-2.0 許可證。