Wav2vec2 Large XLSR 53 A Portuguese

🚀 Wav2Vec2-Large-XLSR-53-Portuguese

このモデルは、Common Voice データセットを使用してポルトガル語で facebook/wav2vec2-large-xlsr-53 をファインチューニングしたものです。

🚀 クイックスタート

💻 使用例

基本的な使用法

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

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

processor = Wav2Vec2Processor.from_pretrained("Rubens/Wav2Vec2-Large-XLSR-53-a-Portuguese")
model = Wav2Vec2ForCTC.from_pretrained("Rubens/Wav2Vec2-Large-XLSR-53-a-Portuguese")

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

# Preprocessing the datasets.
# We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
\treturn 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():
\tlogits = 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])

高度な使用法

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

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

processor = Wav2Vec2Processor.from_pretrained("Rubens/Wav2Vec2-Large-XLSR-53-a-Portuguese")
model = Wav2Vec2ForCTC.from_pretrained("Rubens/Wav2Vec2-Large-XLSR-53-a-Portuguese")
model.to("cuda")

chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\\"\\“]'  # TODO: adapt this list to include all special characters you removed from the data
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):
\tbatch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
\treturn 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):
\tinputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)

\twith torch.no_grad():
\t\tlogits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits

  pred_ids = torch.argmax(logits, dim=-1)
\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
\treturn 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"])))

テスト結果(WER): 19.30 %

🔧 技術詳細

Common Voice の train と validation データセットをトレーニングに使用しました。

トレーニングに使用したスクリプトはこちらにあります: https://github.com/RubensZimbres/wav2vec2/blob/main/fine-tuning.py

📄 ライセンス

このモデルは Apache-2.0 ライセンスの下で提供されています。