File size: 9,625 Bytes
24829a1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7f7f412
24829a1
 
7f7f412
24829a1
 
7f7f412
24829a1
1b12cc3
 
 
 
c8546f3
 
1b12cc3
24829a1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a32e829
 
 
 
 
 
 
 
 
 
24829a1
a32e829
 
 
 
 
 
 
 
 
 
 
 
 
24829a1
a32e829
 
 
 
 
 
 
 
 
 
 
 
 
 
24829a1
 
 
 
 
 
 
 
 
 
c8546f3
86ac495
 
 
24829a1
86ac495
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24829a1
86ac495
 
 
 
 
 
 
 
 
 
 
 
24829a1
86ac495
 
 
 
24829a1
86ac495
 
 
 
 
 
 
 
 
24829a1
86ac495
 
c8546f3
86ac495
 
 
 
 
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
from encoder.params_model import model_embedding_size as speaker_embedding_size
from utils.argutils import print_args
from utils.modelutils import check_model_paths
from synthesizer.inference import Synthesizer
from encoder import inference as encoder
from vocoder import inference as vocoder
from pathlib import Path
import numpy as np
import soundfile as sf
import librosa
import argparse
import torch
import sys
import os
from audioread.exceptions import NoBackendError

if __name__ == '__main__':
    ## Info & args
    parser = argparse.ArgumentParser(
        formatter_class=argparse.ArgumentDefaultsHelpFormatter
    )
    parser.add_argument("-e", "--enc_model_fpath", type=Path, 
                        default="encpretrained.pt",
                        help="Path to a saved encoder")
    parser.add_argument("-s", "--syn_model_fpath", type=Path, 
                        default="synpretrained.pt",
                        help="Path to a saved synthesizer")
    parser.add_argument("-v", "--voc_model_fpath", type=Path, 
                        default="vocpretrained.pt",
                        help="Path to a saved vocoder")
    parser.add_argument("--cpu", action="store_true", help="If True, processing is done on CPU, even when a GPU is available.")
    parser.add_argument("--no_sound", action="store_true", help="If True, audio won't be played.")
    parser.add_argument("--seed", type=int, default=None, help="Optional random number seed value to make toolbox deterministic.")
    parser.add_argument("--no_mp3_support", action="store_true", help="If True, disallows loading mp3 files to prevent audioread errors when ffmpeg is not installed.")
    parser.add_argument("-audio", "--audio_path", type=Path, required = True,
                        help="Path to a audio file")
    parser.add_argument("--text", type=str, required = True, help="Text Input")
    args = parser.parse_args()
    print_args(args, parser)
    if not args.no_sound:
        import sounddevice as sd

    if args.cpu:
        # Hide GPUs from Pytorch to force CPU processing
        os.environ["CUDA_VISIBLE_DEVICES"] = "-1"

    if not args.no_mp3_support:
        try:
            librosa.load("samples/1320_00000.mp3")
        except NoBackendError:
            print("Librosa will be unable to open mp3 files if additional software is not installed.\n"
                  "Please install ffmpeg or add the '--no_mp3_support' option to proceed without support for mp3 files.")
            exit(-1)
        
    print("Running a test of your configuration...\n")
        
    if torch.cuda.is_available():
        device_id = torch.cuda.current_device()
        gpu_properties = torch.cuda.get_device_properties(device_id)
        ## Print some environment information (for debugging purposes)
        print("Found %d GPUs available. Using GPU %d (%s) of compute capability %d.%d with "
            "%.1fGb total memory.\n" % 
            (torch.cuda.device_count(),
            device_id,
            gpu_properties.name,
            gpu_properties.major,
            gpu_properties.minor,
            gpu_properties.total_memory / 1e9))
    else:
        print("Using CPU for inference.\n")
    
    ## Remind the user to download pretrained models if needed
    check_model_paths(encoder_path=args.enc_model_fpath,
                      synthesizer_path=args.syn_model_fpath,
                      vocoder_path=args.voc_model_fpath)
    
    ## Load the models one by one.
    print("Preparing the encoder, the synthesizer and the vocoder...")
    encoder.load_model(args.enc_model_fpath)
    synthesizer = Synthesizer(args.syn_model_fpath)
    vocoder.load_model(args.voc_model_fpath)
    
    
    ## Run a test
    # print("Testing your configuration with small inputs.")
    # # Forward an audio waveform of zeroes that lasts 1 second. Notice how we can get the encoder's
    # # sampling rate, which may differ.
    # # If you're unfamiliar with digital audio, know that it is encoded as an array of floats 
    # # (or sometimes integers, but mostly floats in this projects) ranging from -1 to 1.
    # # The sampling rate is the number of values (samples) recorded per second, it is set to
    # # 16000 for the encoder. Creating an array of length <sampling_rate> will always correspond 
    # # to an audio of 1 second.
    # print("	Testing the encoder...")
    # encoder.embed_utterance(np.zeros(encoder.sampling_rate))
    
    # # Create a dummy embedding. You would normally use the embedding that encoder.embed_utterance
    # # returns, but here we're going to make one ourselves just for the sake of showing that it's
    # # possible.
    # embed = np.random.rand(speaker_embedding_size)
    # # Embeddings are L2-normalized (this isn't important here, but if you want to make your own 
    # # embeddings it will be).
    # embed /= np.linalg.norm(embed)
    # # The synthesizer can handle multiple inputs with batching. Let's create another embedding to 
    # # illustrate that
    # embeds = [embed, np.zeros(speaker_embedding_size)]
    # texts = ["test 1", "test 2"]
    # print("	Testing the synthesizer... (loading the model will output a lot of text)")
    # mels = synthesizer.synthesize_spectrograms(texts, embeds)
    
    # # The vocoder synthesizes one waveform at a time, but it's more efficient for long ones. We 
    # # can concatenate the mel spectrograms to a single one.
    # mel = np.concatenate(mels, axis=1)
    # # The vocoder can take a callback function to display the generation. More on that later. For 
    # # now we'll simply hide it like this:
    # no_action = lambda *args: None
    # print("	Testing the vocoder...")
    # # For the sake of making this test short, we'll pass a short target length. The target length 
    # # is the length of the wav segments that are processed in parallel. E.g. for audio sampled 
    # # at 16000 Hertz, a target length of 8000 means that the target audio will be cut in chunks of
    # # 0.5 seconds which will all be generated together. The parameters here are absurdly short, and 
    # # that has a detrimental effect on the quality of the audio. The default parameters are 
    # # recommended in general.
    # vocoder.infer_waveform(mel, target=200, overlap=50, progress_callback=no_action)
    
    print("All test passed! You can now synthesize speech.\n\n")
    
    
    ## Interactive speech generation
    print("This is a GUI-less example of interface to SV2TTS. The purpose of this script is to "
          "show how you can interface this project easily with your own. See the source code for "
          "an explanation of what is happening.\n")
    
    print("Interactive generation loop")
    # while True:
    # Get the reference audio filepath
    message = "Reference voice: enter an audio filepath of a voice to be cloned (mp3, "                   "wav, m4a, flac, ...):\n"
    in_fpath = args.audio_path

    if in_fpath.suffix.lower() == ".mp3" and args.no_mp3_support:
        print("Can't Use mp3 files please try again:")
    ## Computing the embedding
    # First, we load the wav using the function that the speaker encoder provides. This is 
    # important: there is preprocessing that must be applied.
    
    # The following two methods are equivalent:
    # - Directly load from the filepath:
    preprocessed_wav = encoder.preprocess_wav(in_fpath)
    # - If the wav is already loaded:
    original_wav, sampling_rate = librosa.load(str(in_fpath))
    preprocessed_wav = encoder.preprocess_wav(original_wav, sampling_rate)
    print("Loaded file succesfully")
    
    # Then we derive the embedding. There are many functions and parameters that the 
    # speaker encoder interfaces. These are mostly for in-depth research. You will typically
    # only use this function (with its default parameters):
    embed = encoder.embed_utterance(preprocessed_wav)
    print("Created the embedding")
    
    
    ## Generating the spectrogram
    text = args.text
    
    # If seed is specified, reset torch seed and force synthesizer reload
    if args.seed is not None:
        torch.manual_seed(args.seed)
        synthesizer = Synthesizer(args.syn_model_fpath)

    # The synthesizer works in batch, so you need to put your data in a list or numpy array
    texts = [text]
    embeds = [embed]
    # If you know what the attention layer alignments are, you can retrieve them here by
    # passing return_alignments=True
    specs = synthesizer.synthesize_spectrograms(texts, embeds)
    spec = specs[0]
    print("Created the mel spectrogram")
    
    
    ## Generating the waveform
    print("Synthesizing the waveform:")

    # If seed is specified, reset torch seed and reload vocoder
    if args.seed is not None:
        torch.manual_seed(args.seed)
        vocoder.load_model(args.voc_model_fpath)

    # Synthesizing the waveform is fairly straightforward. Remember that the longer the
    # spectrogram, the more time-efficient the vocoder.
    generated_wav = vocoder.infer_waveform(spec)
    
    
    ## Post-generation
    # There's a bug with sounddevice that makes the audio cut one second earlier, so we
    # pad it.
    generated_wav = np.pad(generated_wav, (0, synthesizer.sample_rate), mode="constant")

    # Trim excess silences to compensate for gaps in spectrograms (issue #53)
    generated_wav = encoder.preprocess_wav(generated_wav)
        
    # Save it on the disk
    filename = "demo_output_1.wav"
    print(generated_wav.dtype)
    sf.write(filename, generated_wav.astype(np.float32), synthesizer.sample_rate)
    print("\nSaved output as %s\n\n" % filename)