Wav2vec2 Indonesian Javanese Sundanese

🚀 印尼語多語言語音識別模型

本模型是為 印尼語多語言語音識別 項目構建的。它是在 Facebook的Wav2Vec2-large-xlsr-53 基礎上，針對 印尼語Common Voice數據集、爪哇語高質量TTS數據 - SLR41 和 巽他語高質量TTS數據 - SLR44 進行微調得到的。

我們還提供了一個 在線演示 來測試該模型。

使用此模型時，請確保語音輸入的採樣率為16kHz。

🚀 快速開始

本模型專為 印尼語多語言語音識別 項目而構建。它基於 facebook/wav2vec2-large-xlsr-53 模型，並針對 印尼語Common Voice數據集、爪哇語高質量TTS數據 - SLR41 和 巽他語高質量TTS數據 - SLR44 進行了微調。

同時，我們提供了 在線演示 供您測試模型。使用時，請確保語音輸入的採樣率為16kHz。

✨ 主要特性

• 多語言支持：支持印尼語（id）、爪哇語（jv）和巽他語（sun）。
• 微調優化：基於 facebook/wav2vec2-large-xlsr-53 模型在多個數據集上進行微調。
• 即時演示：提供 在線演示 方便測試。

📦 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", "id", split="test[:2%]")

processor = Wav2Vec2Processor.from_pretrained("indonesian-nlp/wav2vec2-indonesian-javanese-sundanese")
model = Wav2Vec2ForCTC.from_pretrained("indonesian-nlp/wav2vec2-indonesian-javanese-sundanese")

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[:2]["speech"], 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[:2]["sentence"])

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", "id", split="test")
wer = load_metric("wer")

processor = Wav2Vec2Processor.from_pretrained("indonesian-nlp/wav2vec2-indonesian-javanese-sundanese")
model = Wav2Vec2ForCTC.from_pretrained("indonesian-nlp/wav2vec2-indonesian-javanese-sundanese") 
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"] = 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 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

評估

該模型可在Common Voice的印尼語測試數據上進行如下評估：

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

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

processor = Wav2Vec2Processor.from_pretrained("indonesian-nlp/wav2vec2-indonesian-javanese-sundanese")
model = Wav2Vec2ForCTC.from_pretrained("indonesian-nlp/wav2vec2-indonesian-javanese-sundanese") 
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"] = 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 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"])))

測試結果：11.57 %

訓練

使用了Common Voice的 train、validation 等數據集進行訓練。訓練腳本可在 此處 找到（即將發佈）。

🔧 技術細節

文檔未提供足夠的技術實現細節，故跳過此章節。

📄 許可證

本模型採用 apache-2.0 許可證。

📋 模型信息

📊 模型結果