Wav2vec2 Large Xlsr Upper Sorbian Mixed

🚀 Wav2Vec2-Large-XLSR-Upper-Sorbian

本項目是在Upper Sorbian Common Voice數據集上對 facebook/wav2vec2-large-xlsr-53 進行微調得到的模型，此外還加入了來自在線 Sorbian課程 的28分鐘額外音頻。

使用此模型時，請確保輸入的語音採樣率為16kHz。

🚀 快速開始

本模型是在Upper Sorbian Common Voice數據集上對預訓練模型進行微調得到的，可用於上索布語的語音識別任務。使用時需注意語音輸入的採樣率。

✨ 主要特性

• 基於預訓練模型 facebook/wav2vec2-large-xlsr-53 進行微調。
• 結合了 Upper Sorbian Common Voice數據集 和在線課程的額外音頻數據。
• 可用於上索布語的自動語音識別任務。

📦 安裝指南

文檔未提及具體安裝步驟，故跳過此章節。

💻 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", "hsb", split="test[:2%]")
processor = Wav2Vec2Processor.from_pretrained("jimregan/wav2vec2-large-xlsr-upper-sorbian-mixed")
model = Wav2Vec2ForCTC.from_pretrained("jimregan/wav2vec2-large-xlsr-upper-sorbian-mixed")
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):
    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", "ga-IE", split="test")
wer = load_metric("wer")
processor = Wav2Vec2Processor.from_pretrained("jimregan/wav2vec2-large-xlsr-upper-sorbian-mixed")
model = Wav2Vec2ForCTC.from_pretrained("jimregan/wav2vec2-large-xlsr-upper-sorbian-mixed")
model.to("cuda")
chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\“\\\\\\\\\\\\\\\\%\\\\\\\\\\\\\\\\‘\\\\\\\\\\\\\\\\”\\\\\\\\\\\\\\\\�„«»–]'
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):
    batch["sentence"] = remove_special_characters(batch["sentence"])
    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 audio 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"])))

📚 詳細文檔

測試結果

測試結果：48.2 %

訓練信息

• 訓練數據：使用了Common Voice的 train 和 validation 數據集，並結合了在線 Sorbian課程 中英語A1課程的詞彙。
• 訓練腳本：可在 此處 找到。
• 數據清理腳本：用於清理詞彙數據轉錄的腳本在 此處。

📄 許可證

本項目採用 apache-2.0 許可證。

模型信息表格