import sys, os if sys.platform == "darwin": os.environ["PYTORCH_ENABLE_MPS_FALLBACK"] = "1" 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 net_g = None 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 == "JA": 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): global net_g bert, ja_bert, phones, tones, lang_ids = get_text(text, "JP", 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 return audio def tts_fn(text, speaker, sdp_ratio, noise_scale, noise_scale_w, length_scale): with torch.no_grad(): audio = infer(text, sdp_ratio=sdp_ratio, noise_scale=noise_scale, noise_scale_w=noise_scale_w, length_scale=length_scale, sid=speaker) return "Success", (hps.data.sampling_rate, audio) if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--model_dir", default="./logs/Mygo/G_44000.pth", help="path of your model") parser.add_argument("--config_dir", default="./configs/config.json", help="path of your config file") parser.add_argument("--share", default=False, help="make link public") 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_dir) device = "cuda:0" if torch.cuda.is_available() else "cpu" ''' 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_dir, net_g, None, skip_optimizer=True) speaker_ids = hps.data.spk2id speakers = list(speaker_ids.keys()) with gr.Blocks() as app: with gr.Row(): with gr.Column(): gr.Markdown(value=""" Mygo Vits-bert """) text = gr.TextArea(label="Text", placeholder="Input Text Here", value="私たちは、一緒にはいられない。") 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/DP混合比') noise_scale = gr.Slider(minimum=0.1, maximum=1.5, value=0.6, step=0.1, label='感情调节') noise_scale_w = gr.Slider(minimum=0.1, maximum=1.4, value=0.8, step=0.1, label='音素长度') length_scale = gr.Slider(minimum=0.1, maximum=2, value=1, step=0.1, label='生成长度') btn = gr.Button("生成!", variant="primary") with gr.Column(): text_output = gr.Textbox(label="Message") audio_output = gr.Audio(label="Output Audio") btn.click(tts_fn, inputs=[text, speaker, sdp_ratio, noise_scale, noise_scale_w, length_scale], outputs=[text_output, audio_output]) # webbrowser.open("http://127.0.0.1:6006") # app.launch(server_port=6006, show_error=True) app.launch(show_error=True)