File size: 8,374 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
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
# 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 numpy as np
import torch
import torchaudio
import argparse


from text.g2p_module import G2PModule
from utils.tokenizer import AudioTokenizer, tokenize_audio
from models.tts.valle.valle import VALLE
from models.tts.base.tts_inferece import TTSInference
from models.tts.valle.valle_dataset import VALLETestDataset, VALLETestCollator
from processors.phone_extractor import phoneExtractor
from text.text_token_collation import phoneIDCollation


class VALLEInference(TTSInference):
    def __init__(self, args=None, cfg=None):
        TTSInference.__init__(self, args, cfg)

        self.g2p_module = G2PModule(backend=self.cfg.preprocess.phone_extractor)
        text_token_path = os.path.join(
            cfg.preprocess.processed_dir, cfg.dataset[0], cfg.preprocess.symbols_dict
        )
        self.audio_tokenizer = AudioTokenizer()

    def _build_model(self):
        model = VALLE(self.cfg.model)
        return model

    def _build_test_dataset(self):
        return VALLETestDataset, VALLETestCollator

    def inference_one_clip(self, text, text_prompt, audio_file, save_name="pred"):
        # 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)
        # convert phone sequence to phone id sequence
        phon_id_collator = phoneIDCollation(
            self.cfg, symbols_dict_file=phone_symbol_file
        )

        text = f"{text_prompt} {text}".strip()
        phone_seq = phone_extractor.extract_phone(text)  # phone_seq: list
        phone_id_seq = phon_id_collator.get_phone_id_sequence(self.cfg, phone_seq)
        phone_id_seq_len = torch.IntTensor([len(phone_id_seq)]).to(self.device)

        # convert phone sequence to phone id sequence
        phone_id_seq = np.array([phone_id_seq])
        phone_id_seq = torch.from_numpy(phone_id_seq).to(self.device)

        # extract acoustic token
        encoded_frames = tokenize_audio(self.audio_tokenizer, audio_file)
        audio_prompt_token = encoded_frames[0][0].transpose(2, 1).to(self.device)

        # copysyn
        if self.args.copysyn:
            samples = self.audio_tokenizer.decode(encoded_frames)
            audio_copysyn = samples[0].cpu().detach()

            out_path = os.path.join(
                self.args.output_dir, self.infer_type, f"{save_name}_copysyn.wav"
            )
            torchaudio.save(out_path, audio_copysyn, self.cfg.preprocess.sampling_rate)

        if self.args.continual:
            encoded_frames = self.model.continual(
                phone_id_seq,
                phone_id_seq_len,
                audio_prompt_token,
            )
        else:
            enroll_x_lens = None
            if text_prompt:
                # prompt_phone_seq = tokenize_text(self.g2p_module, text=f"{text_prompt}".strip())
                # _, enroll_x_lens = self.text_tokenizer.get_token_id_seq(prompt_phone_seq)

                text = f"{text_prompt}".strip()
                prompt_phone_seq = phone_extractor.extract_phone(
                    text
                )  # phone_seq: list
                prompt_phone_id_seq = phon_id_collator.get_phone_id_sequence(
                    self.cfg, prompt_phone_seq
                )
                prompt_phone_id_seq_len = torch.IntTensor(
                    [len(prompt_phone_id_seq)]
                ).to(self.device)

            encoded_frames = self.model.inference(
                phone_id_seq,
                phone_id_seq_len,
                audio_prompt_token,
                enroll_x_lens=prompt_phone_id_seq_len,
                top_k=self.args.top_k,
                temperature=self.args.temperature,
            )

        samples = self.audio_tokenizer.decode([(encoded_frames.transpose(2, 1), None)])

        audio = samples[0].squeeze(0).cpu().detach()

        return audio

    def inference_for_single_utterance(self):
        text = self.args.text
        text_prompt = self.args.text_prompt
        audio_file = self.args.audio_prompt

        if not self.args.continual:
            assert text != ""
        else:
            text = ""
        assert text_prompt != ""
        assert audio_file != ""

        audio = self.inference_one_clip(text, text_prompt, audio_file)

        return audio

    def inference_for_batches(self):
        test_list_file = self.args.test_list_file
        assert test_list_file is not None

        pred_res = []
        with open(test_list_file, "r") as fin:
            for idx, line in enumerate(fin.readlines()):
                fields = line.strip().split("|")
                if self.args.continual:
                    assert len(fields) == 2
                    text_prompt, audio_prompt_path = fields
                    text = ""
                else:
                    assert len(fields) == 3
                    text_prompt, audio_prompt_path, text = fields

                audio = self.inference_one_clip(
                    text, text_prompt, audio_prompt_path, str(idx)
                )
                pred_res.append(audio)

        return pred_res

        """
        TODO: batch inference 
        ###### Construct test_batch ######
        n_batch = len(self.test_dataloader)
        now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(time.time()))
        print(
            "Model eval time: {}, batch_size = {}, n_batch = {}".format(
                now, self.test_batch_size, n_batch
            )
        )       
        
        ###### Inference for each batch ######
        pred_res = []
        with torch.no_grad():
            for i, batch_data in enumerate(
                self.test_dataloader if n_batch == 1 else tqdm(self.test_dataloader)
            ):
                if self.args.continual:
                    encoded_frames = self.model.continual(
                        batch_data["phone_seq"],
                        batch_data["phone_len"],
                        batch_data["acoustic_token"],
                    )
                else:
                    encoded_frames = self.model.inference(
                        batch_data["phone_seq"],
                        batch_data["phone_len"],
                        batch_data["acoustic_token"],
                        enroll_x_lens=batch_data["pmt_phone_len"],
                        top_k=self.args.top_k,
                        temperature=self.args.temperature
                    )
                    
                samples = self.audio_tokenizer.decode(
                    [(encoded_frames.transpose(2, 1), None)]
                )
                
                            
                for idx in range(samples.size(0)):
                    audio = samples[idx].cpu()
                    pred_res.append(audio)
                    
        return pred_res
        """

    def add_arguments(parser: argparse.ArgumentParser):
        parser.add_argument(
            "--text_prompt",
            type=str,
            default="",
            help="Text prompt that should be aligned with --audio_prompt.",
        )

        parser.add_argument(
            "--audio_prompt",
            type=str,
            default="",
            help="Audio prompt that should be aligned with --text_prompt.",
        )
        parser.add_argument(
            "--top-k",
            type=int,
            default=-100,
            help="Whether AR Decoder do top_k(if > 0) sampling.",
        )

        parser.add_argument(
            "--temperature",
            type=float,
            default=1.0,
            help="The temperature of AR Decoder top_k sampling.",
        )

        parser.add_argument(
            "--continual",
            action="store_true",
            help="Inference for continual task.",
        )

        parser.add_argument(
            "--copysyn",
            action="store_true",
            help="Copysyn: generate audio by decoder of the original audio tokenizer.",
        )