Spaces:
Running
on
Zero
Running
on
Zero
File size: 6,991 Bytes
c968fc3 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 |
# Copyright (c) 2023 Amphion.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.
import os
import torch
from tqdm import tqdm
from collections import OrderedDict
from models.tts.base.tts_inferece import TTSInference
from models.tts.fastspeech2.fs2_dataset import FS2TestDataset, FS2TestCollator
from utils.util import load_config
from utils.io import save_audio
from models.tts.fastspeech2.fs2 import FastSpeech2
from models.vocoders.vocoder_inference import synthesis
from pathlib import Path
from processors.phone_extractor import phoneExtractor
from text.text_token_collation import phoneIDCollation
import numpy as np
import json
class FastSpeech2Inference(TTSInference):
def __init__(self, args, cfg):
TTSInference.__init__(self, args, cfg)
self.args = args
self.cfg = cfg
self.infer_type = args.mode
def _build_model(self):
self.model = FastSpeech2(self.cfg)
return self.model
def load_model(self, state_dict):
raw_dict = state_dict["model"]
clean_dict = OrderedDict()
for k, v in raw_dict.items():
if k.startswith("module."):
clean_dict[k[7:]] = v
else:
clean_dict[k] = v
self.model.load_state_dict(clean_dict)
def _build_test_dataset(self):
return FS2TestDataset, FS2TestCollator
@staticmethod
def _parse_vocoder(vocoder_dir):
r"""Parse vocoder config"""
vocoder_dir = os.path.abspath(vocoder_dir)
ckpt_list = [ckpt for ckpt in Path(vocoder_dir).glob("*.pt")]
# last step (different from the base *int(x.stem)*)
ckpt_list.sort(
key=lambda x: int(x.stem.split("_")[-2].split("-")[-1]), reverse=True
)
ckpt_path = str(ckpt_list[0])
vocoder_cfg = load_config(
os.path.join(vocoder_dir, "args.json"), lowercase=True
)
return vocoder_cfg, ckpt_path
@torch.inference_mode()
def inference_for_batches(self):
y_pred = []
for i, batch in tqdm(enumerate(self.test_dataloader)):
y_pred, mel_lens, _ = self._inference_each_batch(batch)
y_ls = y_pred.chunk(self.test_batch_size)
tgt_ls = mel_lens.chunk(self.test_batch_size)
j = 0
for it, l in zip(y_ls, tgt_ls):
l = l.item()
it = it.squeeze(0)[:l].detach().cpu()
uid = self.test_dataset.metadata[i * self.test_batch_size + j]["Uid"]
torch.save(it, os.path.join(self.args.output_dir, f"{uid}.pt"))
j += 1
vocoder_cfg, vocoder_ckpt = self._parse_vocoder(self.args.vocoder_dir)
res = synthesis(
cfg=vocoder_cfg,
vocoder_weight_file=vocoder_ckpt,
n_samples=None,
pred=[
torch.load(
os.path.join(self.args.output_dir, "{}.pt".format(item["Uid"]))
).numpy()
for item in self.test_dataset.metadata
],
)
for it, wav in zip(self.test_dataset.metadata, res):
uid = it["Uid"]
save_audio(
os.path.join(self.args.output_dir, f"{uid}.wav"),
wav.numpy(),
self.cfg.preprocess.sample_rate,
add_silence=True,
turn_up=True,
)
os.remove(os.path.join(self.args.output_dir, f"{uid}.pt"))
@torch.inference_mode()
def _inference_each_batch(self, batch_data):
device = self.accelerator.device
control_values = (
self.args.pitch_control,
self.args.energy_control,
self.args.duration_control,
)
for k, v in batch_data.items():
batch_data[k] = v.to(device)
pitch_control, energy_control, duration_control = control_values
output = self.model(
batch_data,
p_control=pitch_control,
e_control=energy_control,
d_control=duration_control,
)
pred_res = output["postnet_output"]
mel_lens = output["mel_lens"].cpu()
return pred_res, mel_lens, 0
def inference_for_single_utterance(self):
text = self.args.text
control_values = (
self.args.pitch_control,
self.args.energy_control,
self.args.duration_control,
)
pitch_control, energy_control, duration_control = control_values
# get phone symbol file
phone_symbol_file = None
if self.cfg.preprocess.phone_extractor != "lexicon":
phone_symbol_file = os.path.join(
self.exp_dir, self.cfg.preprocess.symbols_dict
)
assert os.path.exists(phone_symbol_file)
# convert text to phone sequence
phone_extractor = phoneExtractor(self.cfg)
phone_seq = phone_extractor.extract_phone(text) # phone_seq: list
# convert phone sequence to phone id sequence
phon_id_collator = phoneIDCollation(
self.cfg, symbols_dict_file=phone_symbol_file
)
phone_seq = ["{"] + phone_seq + ["}"]
phone_id_seq = phon_id_collator.get_phone_id_sequence(self.cfg, phone_seq)
# convert phone sequence to phone id sequence
phone_id_seq = np.array(phone_id_seq)
phone_id_seq = torch.from_numpy(phone_id_seq)
# get speaker id if multi-speaker training and use speaker id
speaker_id = None
if self.cfg.preprocess.use_spkid and self.cfg.train.multi_speaker_training:
spk2id_file = os.path.join(self.exp_dir, self.cfg.preprocess.spk2id)
with open(spk2id_file, "r") as f:
spk2id = json.load(f)
speaker_id = spk2id[self.args.speaker_name]
speaker_id = torch.from_numpy(np.array([speaker_id], dtype=np.int32))
else:
speaker_id = torch.Tensor(0).view(-1)
with torch.no_grad():
x_tst = phone_id_seq.to(self.device).unsqueeze(0)
x_tst_lengths = torch.LongTensor([phone_id_seq.size(0)]).to(self.device)
if speaker_id is not None:
speaker_id = speaker_id.to(self.device)
data = {}
data["texts"] = x_tst
data["text_len"] = x_tst_lengths
data["spk_id"] = speaker_id
output = self.model(
data,
p_control=pitch_control,
e_control=energy_control,
d_control=duration_control,
)
pred_res = output["postnet_output"]
vocoder_cfg, vocoder_ckpt = self._parse_vocoder(self.args.vocoder_dir)
audio = synthesis(
cfg=vocoder_cfg,
vocoder_weight_file=vocoder_ckpt,
n_samples=None,
pred=pred_res,
)
return audio[0]
|