Wav2vec2 Large Xlsr 53 Hungarian

🚀 wav2vec2-large-xlsr-53-hungarian

這個模型是 facebook/wav2vec2-large-xlsr-53 在 MOZILLA-FOUNDATION/COMMON_VOICE_17_0 - HU 數據集上的微調版本。它能夠將語音數據轉換為文本，在語音識別領域有重要應用價值。

🚀 快速開始

這個模型是 facebook/wav2vec2-large-xlsr-53 在 MOZILLA-FOUNDATION/COMMON_VOICE_17_0 - HU 數據集上的微調版本。它在評估集上取得了以下結果：

• 損失值：0.1748
• 詞錯誤率（Wer）：0.2997

由於忽略了部分字符，訓練和測量的詞錯誤率值有所不同。

✨ 主要特性

模型對比

與之前最佳的 wav2vec 模型（在 CV17 上評估）相比，本模型表現更優：

評估時忽略的字符如下：

CHARS_TO_IGNORE = [",", "?", "¿", ".", "!", "¡", ";", "；", ":", '""', "%", '"', "�", "ʿ", "·", "჻", "~", "՞",
                   "؟", "،", "।", "॥", "«", "»", "„", "“", "”", "「", "」", "‘", "’", "《", "》", "(", ")", "[", "]",
                   "{", "}", "=", "`", "_", "+", "<", ">", "…", "–", "°", "´", "ʾ", "‹", "›", "©", "®", "—", "→", "。",
                   "、", "﹂", "﹁", "‧", "～", "﹏", "，", "｛", "｝", "（", "）", "［", "］", "【", "】", "‥", "〽",
                   "『", "』", "〝", "〟", "⟨", "⟩", "〜", "：", "！", "？", "♪", "؛", "/", "\\", "º", "−", "^", "ʻ", "ˆ"]

💻 使用示例

基礎用法

import torch
import librosa
import re
import warnings
from datasets import load_dataset
import evaluate
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor

LANG_ID = "hu"
MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-hungarian"
DEVICE = "cuda"

CHARS_TO_IGNORE = [",", "?", "¿", ".", "!", "¡", ";", "；", ":", '""', "%", '"', "�", "ʿ", "·", "჻", "~", "՞",
                   "؟", "،", "।", "॥", "«", "»", "„", "“", "”", "「", "」", "‘", "’", "《", "》", "(", ")", "[", "]",
                   "{", "}", "=", "`", "_", "+", "<", ">", "…", "–", "°", "´", "ʾ", "‹", "›", "©", "®", "—", "→", "。",
                   "、", "﹂", "﹁", "‧", "～", "﹏", "，", "｛", "｝", "（", "）", "［", "］", "【", "】", "‥", "〽",
                   "『", "』", "〝", "〟", "⟨", "⟩", "〜", "：", "！", "？", "♪", "؛", "/", "\\", "º", "−", "^", "ʻ", "ˆ"]

test_dataset = load_dataset("mozilla-foundation/common_voice_17_0", LANG_ID, split="test")

wer = evaluate.load("wer")  # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/wer.py
cer = evaluate.load("cer")  # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/cer.py


chars_to_ignore_regex = f"[{re.escape(''.join(CHARS_TO_IGNORE))}]"

processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
model.to(DEVICE)

# Preprocessing the datasets.
# We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
    with warnings.catch_warnings():
        warnings.simplefilter("ignore")
        speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
    batch["speech"] = speech_array
    batch["sentence"] = re.sub(chars_to_ignore_regex, "", batch["sentence"]).upper()
    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(DEVICE), attention_mask=inputs.attention_mask.to(DEVICE)).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)

predictions = [x.upper() for x in result["pred_strings"]]
references = [x.upper() for x in result["sentence"]]

print(f"WER: {wer.compute(predictions=predictions, references=references) * 100}")
print(f"CER: {cer.compute(predictions=predictions, references=references) * 100}")

🔧 技術細節

訓練過程

訓練超參數

訓練過程中使用了以下超參數：

• 學習率：0.0003
• 訓練批次大小：16
• 評估批次大小：8
• 隨機種子：42
• 分佈式類型：多 GPU
• 設備數量：2
• 梯度累積步數：2
• 總訓練批次大小：64
• 總評估批次大小：16
• 優化器：使用 OptimizerNames.ADAMW_TORCH，β值為 (0.9, 0.999)，ε值為 1e-08，無額外優化器參數
• 學習率調度器類型：線性
• 學習率調度器熱身步數：500
• 訓練輪數：15.0
• 混合精度訓練：原生 AMP

訓練結果

框架版本

• Transformers 4.50.0.dev0
• Pytorch 2.6.0+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0

📄 許可證

本項目採用 Apache-2.0 許可證。