栩栩如生,音色克隆,Bert-vits2文字轉語音打造鬼畜視訊實踐(Python3.10)

2023-10-23 18:05:43

諸公可知目前最牛逼的TTS免費開源專案是哪一個?沒錯,是Bert-vits2,沒有之一。它是在本來已經極其強大的Vits專案中融入了Bert大模型,基本上解決了VITS的語氣韻律問題,在效果非常出色的情況下訓練的成本開銷普通人也完全可以接受。

BERT的核心思想是通過在大規模文字語料上進行無監督預訓練,學習到通用的語言表示,然後將這些表示用於下游任務的微調。相比傳統的基於詞嵌入的模型,BERT引入了雙向上下文資訊的建模,使得模型能夠更好地理解句子中的語意和關係。

BERT的模型結構基於Transformer,它由多個編碼器層組成。每個編碼器層都有多頭自注意力機制和前饋神經網路,用於對輸入序列進行多層次的特徵提取和表示學習。在預訓練階段,BERT使用了兩種任務來學習語言表示:掩碼語言模型(Masked Language Model,MLM)和下一句預測(Next Sentence Prediction,NSP)。通過這兩種任務,BERT能夠學習到上下文感知的詞嵌入和句子級別的語意表示。

在實際應用中,BERT的預訓練模型可以用於各種下游任務,如文字分類、命名實體識別、問答系統等。通過微調預訓練模型,可以在特定任務上取得更好的效能,而無需從頭開始訓練模型。

BERT的出現對自然語言處理領域帶來了重大影響,成為了許多最新研究和應用的基礎。它在多個任務上取得了領先的效能,並促進了自然語言理解的發展。

本次讓我們基於Bert-vits2專案來克隆渣渣輝和劉青雲的聲音,打造一款時下熱搜榜一的「青島啤酒」鬼畜視訊。

語音素材和模型

首先我們需要渣渣輝和劉青雲的原版音訊素材,原版《掃毒》素材可以參考:https://www.bilibili.com/video/BV1R64y1F7SQ/。

將兩個主角的聲音單獨提取出來,隨後依次進行背景音和前景音的分離,聲音降噪以及聲音切片等操作,這些步驟之前已經做過詳細介紹,請參見:民謠女神唱流行,基於AI人工智慧so-vits庫訓練自己的音色模型(葉蓓/Python3.10)。 囿於篇幅,這裡不再贅述。

做好素材的簡單處理後,我們來克隆專案:

git clone https://github.com/Stardust-minus/Bert-VITS2

隨後安裝專案的依賴:

cd Bert-VITS2  
  
pip3 install -r requirements.txt

接著下載bert模型放入到專案的bert目錄。

bert模型下載地址:

中:https://huggingface.co/hfl/chinese-roberta-wwm-ext-large  
日:https://huggingface.co/cl-tohoku/bert-base-japanese-v3/tree/main

語音標註

接著我們需要對已經切好分片的語音進行標註,這裡我們使用開源庫whisper,關於whisper請移步:聞其聲而知雅意,M1 Mac基於PyTorch(mps/cpu/cuda)的人工智慧AI本地語音識別庫Whisper(Python3.10)

編寫標註程式碼:

import whisper  
import os  
import json  
import torchaudio  
import argparse  
import torch  
  
lang2token = {  
            'zh': "ZH|",  
            'ja': "JP|",  
            "en": "EN|",  
        }  
def transcribe_one(audio_path):  
    # load audio and pad/trim it to fit 30 seconds  
    audio = whisper.load_audio(audio_path)  
    audio = whisper.pad_or_trim(audio)  
  
    # make log-Mel spectrogram and move to the same device as the model  
    mel = whisper.log_mel_spectrogram(audio).to(model.device)  
  
    # detect the spoken language  
    _, probs = model.detect_language(mel)  
    print(f"Detected language: {max(probs, key=probs.get)}")  
    lang = max(probs, key=probs.get)  
    # decode the audio  
    options = whisper.DecodingOptions(beam_size=5)  
    result = whisper.decode(model, mel, options)  
  
    # print the recognized text  
    print(result.text)  
    return lang, result.text  
if __name__ == "__main__":  
    parser = argparse.ArgumentParser()  
    parser.add_argument("--languages", default="CJ")  
    parser.add_argument("--whisper_size", default="medium")  
    args = parser.parse_args()  
    if args.languages == "CJE":  
        lang2token = {  
            'zh': "ZH|",  
            'ja': "JP|",  
            "en": "EN|",  
        }  
    elif args.languages == "CJ":  
        lang2token = {  
            'zh': "ZH|",  
            'ja': "JP|",  
        }  
    elif args.languages == "C":  
        lang2token = {  
            'zh': "ZH|",  
        }  
    assert (torch.cuda.is_available()), "Please enable GPU in order to run Whisper!"  
    model = whisper.load_model(args.whisper_size)  
    parent_dir = "./custom_character_voice/"  
    speaker_names = list(os.walk(parent_dir))[0][1]  
    speaker_annos = []  
    total_files = sum([len(files) for r, d, files in os.walk(parent_dir)])  
    # resample audios  
    # 2023/4/21: Get the target sampling rate  
    with open("./configs/config.json", 'r', encoding='utf-8') as f:  
        hps = json.load(f)  
    target_sr = hps['data']['sampling_rate']  
    processed_files = 0  
    for speaker in speaker_names:  
        for i, wavfile in enumerate(list(os.walk(parent_dir + speaker))[0][2]):  
            # try to load file as audio  
            if wavfile.startswith("processed_"):  
                continue  
            try:  
                wav, sr = torchaudio.load(parent_dir + speaker + "/" + wavfile, frame_offset=0, num_frames=-1, normalize=True,  
                                          channels_first=True)  
                wav = wav.mean(dim=0).unsqueeze(0)  
                if sr != target_sr:  
                    wav = torchaudio.transforms.Resample(orig_freq=sr, new_freq=target_sr)(wav)  
                if wav.shape[1] / sr > 20:  
                    print(f"{wavfile} too long, ignoring\n")  
                save_path = parent_dir + speaker + "/" + f"processed_{i}.wav"  
                torchaudio.save(save_path, wav, target_sr, channels_first=True)  
                # transcribe text  
                lang, text = transcribe_one(save_path)  
                if lang not in list(lang2token.keys()):  
                    print(f"{lang} not supported, ignoring\n")  
                    continue  
                #text = "ZH|" + text + "\n"  
                text = lang2token[lang] + text + "\n"  
                speaker_annos.append(save_path + "|" + speaker + "|" + text)  
                  
                processed_files += 1  
                print(f"Processed: {processed_files}/{total_files}")  
            except:  
                continue

標註後,會生成切片語音對應檔案:

./genshin_dataset/ying/vo_dialog_DPEQ003_raidenEi_01.wav|ying|ZH|神子…臣民對我的畏懼…  
./genshin_dataset/ying/vo_dialog_DPEQ003_raidenEi_02.wav|ying|ZH|我不會那麼做…  
./genshin_dataset/ying/vo_dialog_SGLQ002_raidenEi_01.wav|ying|ZH|不用著急,好好挑選吧,我就在這裡等著。  
./genshin_dataset/ying/vo_dialog_SGLQ003_raidenEi_01.wav|ying|ZH|現在在做的事就是「留影」…  
./genshin_dataset/ying/vo_dialog_SGLQ003_raidenEi_02.wav|ying|ZH|嗯,不錯,又學到新東西了。快開始吧。

說白了,就是通過whisper把人物說的話先轉成文字,並且生成對應的音標:

./genshin_dataset/ying/vo_dialog_DPEQ003_raidenEi_01.wav|ying|ZH|神子…臣民對我的畏懼…|_ sh en z i0 … ch en m in d ui w o d e w ei j v … _|0 2 2 5 5 0 2 2 2 2 4 4 3 3 5 5 4 4 4 4 0 0|1 2 2 1 2 2 2 2 2 2 2 1 1  
./genshin_dataset/ying/vo_dialog_DPEQ003_raidenEi_02.wav|ying|ZH|我不會那麼做…|_ w o b u h ui n a m e z uo … _|0 3 3 2 2 4 4 4 4 5 5 4 4 0 0|1 2 2 2 2 2 2 1 1  
./genshin_dataset/ying/vo_dialog_SGLQ002_raidenEi_01.wav|ying|ZH|不用著急,好好挑選吧,我就在這裡等著.|_ b u y ong zh ao j i , h ao h ao t iao x van b a , w o j iu z ai zh e l i d eng zh e . _|0 2 2 4 4 2 2 2 2 0 2 2 3 3 1 1 3 3 5 5 0 3 3 4 4 4 4 4 4 3 3 3 3 5 5 0 0|1 2 2 2 2 1 2 2 2 2 2 1 2 2 2 2 2 2 2 1 1  
./genshin_dataset/ying/vo_dialog_SGLQ003_raidenEi_01.wav|ying|ZH|現在在做的事就是'留影'…|_ x ian z ai z ai z uo d e sh ir j iu sh ir ' l iu y ing ' … _|0 4 4 4 4 4 4 4 4 5 5 4 4 4 4 4 4 0 2 2 3 3 0 0 0|1 2 2 2 2 2 2 2 2 1 2 2 1 1 1  
./genshin_dataset/ying/vo_dialog_SGLQ003_raidenEi_02.wav|ying|ZH|恩,不錯,又學到新東西了.快開始吧.|_ EE en , b u c uo , y ou x ve d ao x in d ong x i l e . k uai k ai sh ir b a

最後,將標註好的檔案轉換為bert模型可讀檔案:

import torch  
from multiprocessing import Pool  
import commons  
import utils  
from tqdm import tqdm  
from text import cleaned_text_to_sequence, get_bert  
import argparse  
import torch.multiprocessing as mp  
  
  
def process_line(line):  
    rank = mp.current_process()._identity  
    rank = rank[0] if len(rank) > 0 else 0  
    if torch.cuda.is_available():  
        gpu_id = rank % torch.cuda.device_count()  
        device = torch.device(f"cuda:{gpu_id}")  
    wav_path, _, language_str, text, phones, tone, word2ph = line.strip().split("|")  
    phone = phones.split(" ")  
    tone = [int(i) for i in tone.split(" ")]  
    word2ph = [int(i) for i in word2ph.split(" ")]  
    word2ph = [i for i in word2ph]  
    phone, tone, language = cleaned_text_to_sequence(phone, tone, language_str)  
  
    phone = commons.intersperse(phone, 0)  
    tone = commons.intersperse(tone, 0)  
    language = commons.intersperse(language, 0)  
    for i in range(len(word2ph)):  
        word2ph[i] = word2ph[i] * 2  
    word2ph[0] += 1  
  
    bert_path = wav_path.replace(".wav", ".bert.pt")  
  
    try:  
        bert = torch.load(bert_path)  
        assert bert.shape[-1] == len(phone)  
    except Exception:  
        bert = get_bert(text, word2ph, language_str, device)  
        assert bert.shape[-1] == len(phone)  
        torch.save(bert, bert_path)

模型訓練

此時,開啟專案目錄中的config.json檔案:

{  
  "train": {  
    "log_interval": 100,  
    "eval_interval": 100,  
    "seed": 52,  
    "epochs": 200,  
    "learning_rate": 0.0001,  
    "betas": [  
      0.8,  
      0.99  
    ],  
    "eps": 1e-09,  
    "batch_size": 4,  
    "fp16_run": false,  
    "lr_decay": 0.999875,  
    "segment_size": 16384,  
    "init_lr_ratio": 1,  
    "warmup_epochs": 0,  
    "c_mel": 45,  
    "c_kl": 1.0,  
    "skip_optimizer": true  
  },  
  "data": {  
    "training_files": "filelists/train.list",  
    "validation_files": "filelists/val.list",  
    "max_wav_value": 32768.0,  
    "sampling_rate": 44100,  
    "filter_length": 2048,  
    "hop_length": 512,  
    "win_length": 2048,  
    "n_mel_channels": 128,  
    "mel_fmin": 0.0,  
    "mel_fmax": null,  
    "add_blank": true,  
    "n_speakers": 1,  
    "cleaned_text": true,  
    "spk2id": {  
      "ying": 0  
    }  
  },  
  "model": {  
    "use_spk_conditioned_encoder": true,  
    "use_noise_scaled_mas": true,  
    "use_mel_posterior_encoder": false,  
    "use_duration_discriminator": true,  
    "inter_channels": 192,  
    "hidden_channels": 192,  
    "filter_channels": 768,  
    "n_heads": 2,  
    "n_layers": 6,  
    "kernel_size": 3,  
    "p_dropout": 0.1,  
    "resblock": "1",  
    "resblock_kernel_sizes": [  
      3,  
      7,  
      11  
    ],  
    "resblock_dilation_sizes": [  
      [  
        1,  
        3,  
        5  
      ],  
      [  
        1,  
        3,  
        5  
      ],  
      [  
        1,  
        3,  
        5  
      ]  
    ],  
    "upsample_rates": [  
      8,  
      8,  
      2,  
      2,  
      2  
    ],  
    "upsample_initial_channel": 512,  
    "upsample_kernel_sizes": [  
      16,  
      16,  
      8,  
      2,  
      2  
    ],  
    "n_layers_q": 3,  
    "use_spectral_norm": false,  
    "gin_channels": 256  
  }  
}

這裡需要修改的引數是batch_size,通常情況下,數值和本地視訊記憶體應該是一致的,但是最好還是改小一點,比如說一塊4060的8G卡,最好batch_size是4,如果寫8的話,還是有機率爆視訊記憶體。

隨後開始訓練:

python3 train_ms.py

程式返回:

[W C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\distributed\c10d\socket.cpp:601] [c10d] The client socket has failed to connect to [v3u.net]:65280 (system error: 10049 - 在其上下文中,該請求的地址無效。).  
[W C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\distributed\c10d\socket.cpp:601] [c10d] The client socket has failed to connect to [v3u.net]:65280 (system error: 10049 - 在其上下文中,該請求的地址無效。).  
2023-10-23 15:36:08.293 | INFO     | data_utils:_filter:61 - Init dataset...  
100%|█████████████████████████████████████████████████████████████████████████████| 562/562 [00:00<00:00, 14706.57it/s]  
2023-10-23 15:36:08.332 | INFO     | data_utils:_filter:76 - skipped: 0, total: 562  
2023-10-23 15:36:08.333 | INFO     | data_utils:_filter:61 - Init dataset...  
100%|████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:00<?, ?it/s]  
2023-10-23 15:36:08.334 | INFO     | data_utils:_filter:76 - skipped: 0, total: 4  
Using noise scaled MAS for VITS2  
Using duration discriminator for VITS2  
INFO:OUTPUT_MODEL:Loaded checkpoint './logs\OUTPUT_MODEL\DUR_4600.pth' (iteration 33)  
INFO:OUTPUT_MODEL:Loaded checkpoint './logs\OUTPUT_MODEL\G_4600.pth' (iteration 33)  
INFO:OUTPUT_MODEL:Loaded checkpoint './logs\OUTPUT_MODEL\D_4600.pth' (iteration 33)

說明沒有問題,訓練紀錄檔存放在專案的logs目錄下。

隨後可以通過tensorboard來監控訓練過程:

python3 -m tensorboard.main --logdir=logs\OUTPUT_MODEL

當loss趨於穩定說明模型已經收斂:

模型推理

最後,我們就可以使用模型來生成我們想要聽到的語音了:

python3 webui.py -m ./logs\OUTPUT_MODEL\G_47700.pth

注意引數為訓練好的迭代模型,如果覺得當前迭代的模型可用,那麼直接把pth和config.json拷貝出來即可,隨後可以接著訓練下一個模型。

結語

基於Bert-vits2打造的渣渣輝和劉青雲音色的鬼畜視訊已經上線到Youtube(B站),請檢索:劉悅的技術部落格,歡迎諸君品鑑和臻賞。