Wav2vec2 Large Xlsr Pa IN

🚀 Wav2Vec2-Large-XLSR-53-旁遮普語

本項目基於 Common Voice 數據集，在旁遮普語上對 facebook/wav2vec2-large-xlsr-53 模型進行了微調。使用該模型時，請確保語音輸入採樣率為 16kHz。

🔍 模型信息

🚀 快速開始

本模型可直接使用（無需語言模型），以下是使用示例。

💻 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", "pa-IN", split="test[:2%]") 

processor = Wav2Vec2Processor.from_pretrained("danurahul/wav2vec2-large-xlsr-pa-IN") 
model = Wav2Vec2ForCTC.from_pretrained("danurahul/wav2vec2-large-xlsr-pa-IN") 

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])

評估

可在 Common Voice 的旁遮普語測試數據上對模型進行評估，示例代碼如下。

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", "pa-IN", split="test") 

wer = load_metric("wer")

processor = Wav2Vec2Processor.from_pretrained("danurahul/wav2vec2-large-xlsr-pa-IN") 

model = Wav2Vec2ForCTC.from_pretrained("danurahul/wav2vec2-large-xlsr-pa-IN") 

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"])))

測試結果：100 %

訓練

使用 Common Voice 數據集的 train 和 validation 子集進行訓練、驗證和測試。訓練腳本可在 此處 找到。