This model is cool version.
It is suitable for reading explanatory text.
If you want them to speak more emotionally, try the sweet version
If you want them to speak in English, try the English version
If you want them to speak whisper voice, try the ASMR version.
If you want them to speak in Chinese, try the Chinese version
This model is a TTS (text-to-speech) model.
This is a model that has trained style_bert_vits2_jp_extra with my own voice data.
style_bert_vits2_jp_extra is a speech generation model specialized for Japanese.
Compared to previous models, it is possible to generate highly accurate and natural speech.
Since the training data is only the voice of the researcher who created the model,
The license is the same as style_bert_vits2_jp_extra
You can use it freely and free of charge, regardless of whether it is commercial or non-commercial.
モデルを使うときのお約束/limitation
〇できること/What you can do
成果物の加工 Processing of deliverables
成果物の商用利用 Commercial use of deliverables
成果物の学習素材としての利用 Use of deliverables as learning materials
1# At first, we will install the required libraries2!git clone https://github.com/litagin02/Style-Bert-VITS2.git
3%cd Style-Bert-VITS2/4!pip install -r requirements.txt
5!pip install style-bert-vits2 --no-build-isolation # To avoid bugs67# load Japanese bert model8from style_bert_vits2.nlp import bert_models
9from style_bert_vits2.constants import Languages
1011bert_models.load_model(Languages.JP,"ku-nlp/deberta-v2-large-japanese-char-wwm")12bert_models.load_tokenizer(Languages.JP,"ku-nlp/deberta-v2-large-japanese-char-wwm")1314# save model files to model_assets dir15from pathlib import Path
16from huggingface_hub import hf_hub_download
1718model_file ="rikka_botan_cool.safetensors"19config_file ="config.json"20style_file ="style_vectors.npy"2122forfilein[model_file, config_file, style_file]:23print(file)24 hf_hub_download(25"RikkaBotan/style_bert_vits2_jp_extra_cool_original",26file,27 local_dir="model_assets"28)293031# By using saved model, we will test text-to-speech demo32from style_bert_vits2.tts_model import TTSModel
3334assets_root = Path("model_assets")3536model = TTSModel(37 model_path=assets_root / model_file,38 config_path=assets_root / config_file,39 style_vec_path=assets_root / style_file,40 device="cuda"# If you cannot use cuda, please input cpu41)4243# Please input the Japanese text44from IPython.display import Audio, display
4546sr, audio = model.infer(text="ここに文章を入力してください")47display(Audio(audio, rate=sr))
謝辞/Acknowledgments
style-bert-vits2-jp-extraを開発してくださったlitaginさんに感謝いたします。
また、本モデルは多くの研究者さんの努力の上にできています。先人たちの努力に深く感謝します。
We would like to thank Mr./Ms. litagin for developing style-bert-vits2-jp-extra.
Additionally, this model was created based on the efforts of many developers. We are deeply grateful for the efforts of our predecessors.