Apply Code Formatter Change
This commit is contained in:
Stardust-minus
committed by
github-actions[bot]
github-actions[bot]
parent
d82ba3457a
commit
eef212fd00
128
webui.py
128
webui.py
@@ -10,7 +10,9 @@ 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")
|
||||
logging.basicConfig(
|
||||
level=logging.INFO, format="| %(name)s | %(levelname)s | %(message)s"
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -27,6 +29,7 @@ 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)
|
||||
@@ -42,52 +45,101 @@ def get_text(text, language_str, hps):
|
||||
del word2ph
|
||||
assert bert.shape[-1] == len(phone), phone
|
||||
|
||||
if language_str=='ZH':
|
||||
if language_str == "ZH":
|
||||
bert = bert
|
||||
ja_bert = torch.zeros(768, len(phone))
|
||||
elif language_str=="JA":
|
||||
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), (
|
||||
bert.shape, len(phone), sum(word2ph), p1, p2, t1, t2, pold, pold2, word2ph, text, w2pho)
|
||||
bert.shape,
|
||||
len(phone),
|
||||
sum(word2ph),
|
||||
p1,
|
||||
p2,
|
||||
t1,
|
||||
t2,
|
||||
pold,
|
||||
pold2,
|
||||
word2ph,
|
||||
text,
|
||||
w2pho,
|
||||
)
|
||||
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)
|
||||
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()
|
||||
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, language):
|
||||
|
||||
def tts_fn(
|
||||
text, speaker, sdp_ratio, noise_scale, noise_scale_w, length_scale, language
|
||||
):
|
||||
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, language=language)
|
||||
audio = infer(
|
||||
text,
|
||||
sdp_ratio=sdp_ratio,
|
||||
noise_scale=noise_scale,
|
||||
noise_scale_w=noise_scale_w,
|
||||
length_scale=length_scale,
|
||||
sid=speaker,
|
||||
language=language,
|
||||
)
|
||||
torch.cuda.empty_cache()
|
||||
return "Success", (hps.data.sampling_rate, audio)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("-m", "--model", default="./logs/as/G_8000.pth", help="path of your model")
|
||||
parser.add_argument("-c", "--config", default="./configs/config.json", help="path of your config file")
|
||||
parser.add_argument(
|
||||
"-m", "--model", default="./logs/as/G_8000.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")
|
||||
parser.add_argument("-d", "--debug", action="store_true", help="enable DEBUG-LEVEL log")
|
||||
parser.add_argument(
|
||||
"-d", "--debug", action="store_true", help="enable DEBUG-LEVEL log"
|
||||
)
|
||||
|
||||
args = parser.parse_args()
|
||||
if args.debug:
|
||||
@@ -109,33 +161,51 @@ if __name__ == "__main__":
|
||||
hps.data.filter_length // 2 + 1,
|
||||
hps.train.segment_size // hps.data.hop_length,
|
||||
n_speakers=hps.data.n_speakers,
|
||||
**hps.model).to(device)
|
||||
**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","JA"]
|
||||
languages = ["ZH", "JA"]
|
||||
with gr.Blocks() as app:
|
||||
with gr.Row():
|
||||
with gr.Column():
|
||||
text = gr.TextArea(label="Text", placeholder="Input Text Here",
|
||||
value="吃葡萄不吐葡萄皮，不吃葡萄倒吐葡萄皮。")
|
||||
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')
|
||||
text = gr.TextArea(
|
||||
label="Text",
|
||||
placeholder="Input Text Here",
|
||||
value="吃葡萄不吐葡萄皮，不吃葡萄倒吐葡萄皮。",
|
||||
)
|
||||
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!", 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])
|
||||
|
||||
btn.click(
|
||||
tts_fn,
|
||||
inputs=[text, speaker, sdp_ratio, noise_scale, noise_scale_w, length_scale],
|
||||
outputs=[text_output, audio_output],
|
||||
)
|
||||
|
||||
webbrowser.open("http://127.0.0.1:7860")
|
||||
app.launch(share=args.share)
|
||||
|
||||
Reference in New Issue
Block a user