Wav2vec2 Large Xlsr As

🚀 瓦2向量2-大型-XLSR-53-阿薩姆語模型

本項目基於Common Voice數據集，在阿薩姆語上對facebook/wav2vec2-large-xlsr-53模型進行了微調。該模型可用於阿薩姆語的自動語音識別任務，為語音識別領域在阿薩姆語方面提供了有效的解決方案。

🚀 快速開始

在使用此模型時，請確保您的語音輸入採樣率為 16kHz。

✨ 主要特性

• 模型類型：微調後的瓦2向量2（Wav2Vec2）大型XLSR - 53模型。
• 訓練數據：Common Voice阿薩姆語的訓練集和驗證集。
• 評估指標：詞錯誤率（WER），測試集上的WER為 69.63%。

💻 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", "as", split="test[:2%]")
processor = Wav2Vec2Processor.from_pretrained("anuragshas/wav2vec2-large-xlsr-as")
model = Wav2Vec2ForCTC.from_pretrained("anuragshas/wav2vec2-large-xlsr-as")
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])

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", "as", split="test")
wer = load_metric("wer")
processor = Wav2Vec2Processor.from_pretrained("anuragshas/wav2vec2-large-xlsr-as")
model = Wav2Vec2ForCTC.from_pretrained("anuragshas/wav2vec2-large-xlsr-as")
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('’ ',' ',batch["sentence"])
    batch["sentence"] = re.sub(' ‘',' ',batch["sentence"])
    batch["sentence"] = re.sub('’|‘','\'',batch["sentence"])
    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：69.63 %

🔧 技術細節

本模型在訓練時使用了Common Voice的train和validation數據集進行訓練，以提升模型在阿薩姆語語音識別任務上的性能。

📄 許可證

本項目採用 Apache - 2.0 許可證。