W2v Hf Jsut Xlsr53

🚀 日語XLSR Wav2Vec2大模型53

本項目基於 Common Voice 和 JSUT 數據集，在日語上對 facebook/wav2vec2-large-xlsr-53 進行了微調。該模型可用於日語的自動語音識別任務，為語音相關應用提供了強大的支持。

🚀 快速開始

使用此模型時，請確保您的語音輸入採樣率為 16kHz。

✨ 主要特性

• 多數據集微調：基於 Common Voice 和 JSUT 數據集進行微調，提升了模型在日語語音識別上的性能。
• 廣泛的應用場景：適用於音頻、自動語音識別等多個領域。

📦 安裝指南

文檔未提及安裝步驟，暫不展示。

💻 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", "ja", split="test[:2%]")

processor = Wav2Vec2Processor.from_pretrained("qqhann/w2v_hf_jsut_xlsr53")
model = Wav2Vec2ForCTC.from_pretrained("qqhann/w2v_hf_jsut_xlsr53")

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
import MeCab
from jaconv import kata2hira
from typing import List

# Japanese preprocessing
tagger = MeCab.Tagger("-Owakati")
chars_to_ignore_regex = '[\。\、\「\」\,\?\.\!\-\;\:\"\“\%\‘\”\�]'

def text2kata(text):
    node = tagger.parseToNode(text)
    word_class = []
    while node:
        word = node.surface
        wclass = node.feature.split(',')
        if wclass[0] != u'BOS/EOS':
            if len(wclass) <= 6:
                word_class.append((word))
            elif wclass[6] == None:
                word_class.append((word))
            else:
                word_class.append((wclass[6]))
        node = node.next
    return ' '.join(word_class)

def hiragana(text):
    return kata2hira(text2kata(text))

test_dataset = load_dataset("common_voice", "ja", split="test")
wer = load_metric("wer")
resampler = torchaudio.transforms.Resample(48_000, 16_000) # JSUT is already 16kHz
# resampler = torchaudio.transforms.Resample(16_000, 16_000) # JSUT is already 16kHz

processor = Wav2Vec2Processor.from_pretrained("qqhann/w2v_hf_jsut_xlsr53")
model = Wav2Vec2ForCTC.from_pretrained("qqhann/w2v_hf_jsut_xlsr53")
model.to("cuda")


# Preprocessing the datasets.
# We need to read the aduio files as arrays
def speech_file_to_array_fn(batch):
    batch["sentence"] = hiragana(batch["sentence"]).strip()
    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)

def cer_compute(predictions: List[str], references: List[str]):
    p = [" ".join(list(" " + pred.replace(" ", ""))).strip() for pred in predictions]
    r = [" ".join(list(" " + ref.replace(" ", ""))).strip() for ref in references]
    return wer.compute(predictions=p, references=r)

print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
print("CER: {:2f}".format(100 * cer_compute(predictions=result["pred_strings"], references=result["sentence"])))

📚 詳細文檔

模型信息

測試結果

測試結果：字錯率（WER）為 51.72 %

🔧 技術細節

文檔未提供具體的技術實現細節，暫不展示。

📄 許可證

本模型使用的許可證為 Apache-2.0。