Refactor folder structure

toolbox/__init__.py

@@ -1,8 +1,8 @@
 from toolbox.ui import UI
 from encoder import inference as encoder
 from synthesizer.inference import Synthesizer
-from vocoder import inference as rnn_vocoder
-from hifigan import inference as gan_vocoder
+from vocoder.wavernn import inference as rnn_vocoder
+from vocoder.hifigan import inference as gan_vocoder
 from pathlib import Path
 from time import perf_counter as timer
 from toolbox.utterance import Utterance
@@ -50,13 +50,6 @@ MAX_WAVES = 15
 
 class Toolbox:
     def __init__(self, datasets_root, enc_models_dir, syn_models_dir, voc_models_dir, seed, no_mp3_support):
-        if not no_mp3_support:
-            try:
-                librosa.load("samples/6829_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)
         self.no_mp3_support = no_mp3_support
         sys.excepthook = self.excepthook
         self.datasets_root = datasets_root

vocoder/hifigan/inference.py

@@ -1,15 +1,12 @@
 from __future__ import absolute_import, division, print_function, unicode_literals
 
-import glob
 import os
-import argparse
 import json
 import torch
-import numpy as np
 from scipy.io.wavfile import write
-from hifigan.env import AttrDict
-from hifigan.meldataset import mel_spectrogram, MAX_WAV_VALUE, load_wav
-from hifigan.models import Generator
+from vocoder.hifigan.env import AttrDict
+from vocoder.hifigan.meldataset import mel_spectrogram, MAX_WAV_VALUE, load_wav
+from vocoder.hifigan.models import Generator
 import soundfile as sf
 
 
@@ -31,7 +28,7 @@ def load_model(weights_fpath, verbose=True):
     if verbose:
         print("Building hifigan")
 
-    with open("./hifigan/config_16k_.json") as f:
+    with open("./vocoder/hifigan/config_16k_.json") as f:
         data = f.read()
     json_config = json.loads(data)
     h = AttrDict(json_config)

vocoder/hifigan/models.py

@@ -3,7 +3,7 @@ import torch.nn.functional as F
 import torch.nn as nn
 from torch.nn import Conv1d, ConvTranspose1d, AvgPool1d, Conv2d
 from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm
-from hifigan.utils import init_weights, get_padding
+from vocoder.hifigan.utils import init_weights, get_padding
 
 LRELU_SLOPE = 0.1
 

vocoder/wavernn/audio.py

@@ -1,7 +1,7 @@
 import math
 import numpy as np
 import librosa
-import vocoder.hparams as hp
+import vocoder.wavernn.hparams as hp
 from scipy.signal import lfilter
 import soundfile as sf
 

vocoder/wavernn/gen_wavernn.py

@@ -1,5 +1,5 @@
-from vocoder.models.fatchord_version import  WaveRNN
-from vocoder.audio import *
+from vocoder.wavernn.models.fatchord_version import  WaveRNN
+from vocoder.wavernn.audio import *
 
 
 def gen_testset(model: WaveRNN, test_set, samples, batched, target, overlap, save_path):

vocoder/wavernn/inference.py

@@ -1,5 +1,5 @@
-from vocoder.models.fatchord_version import WaveRNN
-from vocoder import hparams as hp
+from vocoder.wavernn.models.fatchord_version import WaveRNN
+from vocoder.wavernn import hparams as hp
 import torch
 
 

vocoder/wavernn/models/fatchord_version.py

@@ -3,7 +3,7 @@ import torch.nn as nn
 import torch.nn.functional as F
 from vocoder.distribution import sample_from_discretized_mix_logistic
 from vocoder.display import *
-from vocoder.audio import *
+from vocoder.wavernn.audio import *
 
 
 class ResBlock(nn.Module):

vocoder/wavernn/train.py

@@ -1,13 +1,13 @@
-from vocoder.models.fatchord_version import WaveRNN
+from vocoder.wavernn.models.fatchord_version import WaveRNN
 from vocoder.vocoder_dataset import VocoderDataset, collate_vocoder
 from vocoder.distribution import discretized_mix_logistic_loss
 from vocoder.display import stream, simple_table
-from vocoder.gen_wavernn import gen_testset
+from vocoder.wavernn.gen_wavernn import gen_testset
 from torch.utils.data import DataLoader
 from pathlib import Path
 from torch import optim
 import torch.nn.functional as F
-import vocoder.hparams as hp
+import vocoder.wavernn.hparams as hp
 import numpy as np
 import time
 import torch

vocoder_train.py

@@ -1,5 +1,5 @@
 from utils.argutils import print_args
-from vocoder.train import train
+from vocoder.wavernn.train import train
 from pathlib import Path
 import argparse