# flake8: noqa: E402 import sys, os import logging logging.getLogger("numba").setLevel(logging.WARNING) logging.getLogger("markdown_it").setLevel(logging.WARNING) logging.getLogger("urllib3").setLevel(logging.WARNING) logging.getLogger("matplotlib").setLevel(logging.WARNING) logging.basicConfig( level=logging.INFO, format="| %(name)s | %(levelname)s | %(message)s" ) logger = logging.getLogger(__name__) import torch import argparse import commons import utils from models import SynthesizerTrn from text.symbols import symbols from text import cleaned_text_to_sequence, get_bert from text.cleaner import clean_text import gradio as gr import webbrowser import numpy as np net_g = None if sys.platform == "darwin" and torch.backends.mps.is_available(): device = "mps" os.environ["PYTORCH_ENABLE_MPS_FALLBACK"] = "1" else: device = "cuda" def get_text(text, language_str, hps): norm_text, phone, tone, word2ph = clean_text(text, language_str) phone, tone, language = cleaned_text_to_sequence(phone, tone, language_str) if hps.data.add_blank: 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 = get_bert(norm_text, word2ph, language_str, device) del word2ph assert bert.shape[-1] == len(phone), phone if language_str == "ZH": bert = bert ja_bert = torch.zeros(768, len(phone)) elif language_str == "JP": ja_bert = bert bert = torch.zeros(1024, len(phone)) else: bert = torch.zeros(1024, len(phone)) ja_bert = torch.zeros(768, len(phone)) assert bert.shape[-1] == len( phone ), f"Bert seq len {bert.shape[-1]} != {len(phone)}" phone = torch.LongTensor(phone) tone = torch.LongTensor(tone) language = torch.LongTensor(language) return bert, ja_bert, phone, tone, language def infer(text, sdp_ratio, noise_scale, noise_scale_w, length_scale, sid, language): global net_g bert, ja_bert, phones, tones, lang_ids = get_text(text, language, hps) with torch.no_grad(): x_tst = phones.to(device).unsqueeze(0) tones = tones.to(device).unsqueeze(0) lang_ids = lang_ids.to(device).unsqueeze(0) bert = bert.to(device).unsqueeze(0) ja_bert = ja_bert.to(device).unsqueeze(0) x_tst_lengths = torch.LongTensor([phones.size(0)]).to(device) del phones speakers = torch.LongTensor([hps.data.spk2id[sid]]).to(device) audio = ( net_g.infer( x_tst, x_tst_lengths, speakers, tones, lang_ids, bert, ja_bert, sdp_ratio=sdp_ratio, noise_scale=noise_scale, noise_scale_w=noise_scale_w, length_scale=length_scale, )[0][0, 0] .data.cpu() .float() .numpy() ) del x_tst, tones, lang_ids, bert, x_tst_lengths, speakers torch.cuda.empty_cache() return audio def tts_fn(text, speaker, sdp_ratio, noise_scale, noise_scale_w, length_scale, language): slices = text.split("|") audio_list = [] with torch.no_grad(): for slice in slices: audio = infer(slice, sdp_ratio=sdp_ratio, noise_scale=noise_scale, noise_scale_w=noise_scale_w, length_scale=length_scale, sid=speaker, language=language) audio_list.append(audio) silence = np.zeros(hps.data.sampling_rate) # 生成1秒的静音 audio_list.append(silence) # 将静音添加到列表中 audio_concat = np.concatenate(audio_list) return "Success", (hps.data.sampling_rate, audio_concat) if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument( "-m", "--model", default="./logs/illi/G_25000.pth", help="path of your model" ) parser.add_argument( "-c", "--config", default="./configs/config.json", help="path of your config file", ) parser.add_argument( "--share", default=False, help="make link public", action="store_true" ) parser.add_argument( "-d", "--debug", action="store_true", help="enable DEBUG-LEVEL log" ) args = parser.parse_args() if args.debug: logger.info("Enable DEBUG-LEVEL log") logging.basicConfig(level=logging.DEBUG) hps = utils.get_hparams_from_file(args.config) device = ( "cuda:0" if torch.cuda.is_available() else ( "mps" if sys.platform == "darwin" and torch.backends.mps.is_available() else "cpu" ) ) net_g = SynthesizerTrn( len(symbols), hps.data.filter_length // 2 + 1, hps.train.segment_size // hps.data.hop_length, n_speakers=hps.data.n_speakers, **hps.model, ).to(device) _ = net_g.eval() _ = utils.load_checkpoint(args.model, net_g, None, skip_optimizer=True) speaker_ids = hps.data.spk2id speakers = list(speaker_ids.keys()) languages = ["ZH", "JP"] with gr.Blocks() as app: with gr.Row(): with gr.Column(): gr.Markdown(value=""" 🤖 【AI以里illi】在线语音合成 Bert-Vits2 🤖\n 📝 作者：Rayzggz 📰博客 https://roi.moe 📺B站 https://space.bilibili.com/10501326 📝\n 🎤 声音来源：以里illi https://space.bilibili.com/3035038 🎤\n 🔗 Bert-VITS2：https://github.com/fishaudio/Bert-VITS2 🔗\n ✅ 使用本模型请遵守中华人民共和国和美利坚合众国法律 ✅\n 🏷️ 使用基于本模型的所有生成内容均需标注「使用Bert-VITS2 AI生成」、「本项目地址」、「作者名称」和「声音来源」 🏷️\n """) text = gr.TextArea( label="Text", placeholder="Input Text Here", value="野生的门卫室魔法师出现了！", ) speaker = gr.Dropdown( choices=speakers, value=speakers[0], label="Speaker" ) sdp_ratio = gr.Slider( minimum=0, maximum=1, value=0.2, step=0.1, label="SDP Ratio" ) noise_scale = gr.Slider( minimum=0.1, maximum=2, value=0.6, step=0.1, label="Noise Scale" ) noise_scale_w = gr.Slider( minimum=0.1, maximum=2, value=0.8, step=0.1, label="Noise Scale W" ) length_scale = gr.Slider( minimum=0.1, maximum=2, value=1, step=0.1, label="Length Scale" ) language = gr.Dropdown( choices=languages, value=languages[0], label="Language" ) btn = gr.Button("Generate 生成!", variant="primary") with gr.Column(): text_output = gr.Textbox(label="Message") audio_output = gr.Audio(label="Output Audio") gr.Markdown(value=""" 👏 鸣谢： 👏\n 👤 团子是咸鱼 https://space.bilibili.com/10685437 👤\n 👤 领航员未鸟 https://space.bilibili.com/2403955 👤\n 👤 Xz乔希 https://space.bilibili.com/5859321 👤\n 👤 怎么好就怎么来 https://space.bilibili.com/259582714 👤\n 🧠 Google Colab https://colab.research.google.com/ 🧠\n 📧 如果你是“以里illi”，并且希望对此模型主张权利，请通过上方“作者”部分的联系方式联系，我将积极配合处理。📧 \n """) btn.click( tts_fn, inputs=[ text, speaker, sdp_ratio, noise_scale, noise_scale_w, length_scale, language, ], outputs=[text_output, audio_output], ) app.launch(show_error=True)