remove unused code

README.md

@@ -0,0 +1,11 @@
+---
+title: KLEA
+emoji: 📈
+colorFrom: indigo
+colorTo: purple
+sdk: gradio
+sdk_version: 3.46.1
+app_file: app.py
+pinned: false
+license: apache-2.0
+---

app.py

@@ -1,7 +1,6 @@
 # -*- coding: utf-8 -*-
 import gradio as gr
 from models import SynthesizerTrn
-from scipy.io.wavfile import write
 from khmer_phonemizer import phonemize_single
 import utils
 import commons

attentions.py

@@ -1,10 +1,7 @@
-import copy
 import math
-import numpy as np
 import torch
 from torch import nn
 from torch.nn import functional as F
-
 import commons
 import modules
 from modules import LayerNorm

commons.py

@@ -1,10 +1,7 @@
 import math
-import numpy as np
 import torch
-from torch import nn
 from torch.nn import functional as F
 
-
 def init_weights(m, mean=0.0, std=0.01):
   classname = m.__class__.__name__
   if classname.find("Conv") != -1:

data_utils.py

@@ -1,392 +0,0 @@
-import time
-import os
-import random
-import numpy as np
-import torch
-import torch.utils.data
-
-import commons 
-from mel_processing import spectrogram_torch
-from utils import load_wav_to_torch, load_filepaths_and_text
-from text import text_to_sequence, cleaned_text_to_sequence
-
-
-class TextAudioLoader(torch.utils.data.Dataset):
-    """
-        1) loads audio, text pairs
-        2) normalizes text and converts them to sequences of integers
-        3) computes spectrograms from audio files.
-    """
-    def __init__(self, audiopaths_and_text, hparams):
-        self.audiopaths_and_text = load_filepaths_and_text(audiopaths_and_text)
-        self.text_cleaners  = hparams.text_cleaners
-        self.max_wav_value  = hparams.max_wav_value
-        self.sampling_rate  = hparams.sampling_rate
-        self.filter_length  = hparams.filter_length 
-        self.hop_length     = hparams.hop_length 
-        self.win_length     = hparams.win_length
-        self.sampling_rate  = hparams.sampling_rate 
-
-        self.cleaned_text = getattr(hparams, "cleaned_text", False)
-
-        self.add_blank = hparams.add_blank
-        self.min_text_len = getattr(hparams, "min_text_len", 1)
-        self.max_text_len = getattr(hparams, "max_text_len", 190)
-
-        random.seed(1234)
-        random.shuffle(self.audiopaths_and_text)
-        self._filter()
-
-
-    def _filter(self):
-        """
-        Filter text & store spec lengths
-        """
-        # Store spectrogram lengths for Bucketing
-        # wav_length ~= file_size / (wav_channels * Bytes per dim) = file_size / (1 * 2)
-        # spec_length = wav_length // hop_length
-
-        audiopaths_and_text_new = []
-        lengths = []
-        for audiopath, text in self.audiopaths_and_text:
-            if self.min_text_len <= len(text) and len(text) <= self.max_text_len:
-                audiopaths_and_text_new.append([audiopath, text])
-                lengths.append(os.path.getsize(audiopath) // (2 * self.hop_length))
-        self.audiopaths_and_text = audiopaths_and_text_new
-        self.lengths = lengths
-
-    def get_audio_text_pair(self, audiopath_and_text):
-        # separate filename and text
-        audiopath, text = audiopath_and_text[0], audiopath_and_text[1]
-        text = self.get_text(text)
-        spec, wav = self.get_audio(audiopath)
-        return (text, spec, wav)
-
-    def get_audio(self, filename):
-        audio, sampling_rate = load_wav_to_torch(filename)
-        if sampling_rate != self.sampling_rate:
-            raise ValueError("{} {} SR doesn't match target {} SR".format(
-                sampling_rate, self.sampling_rate))
-        audio_norm = audio / self.max_wav_value
-        audio_norm = audio_norm.unsqueeze(0)
-        spec_filename = filename.replace(".wav", ".spec.pt")
-        if os.path.exists(spec_filename):
-            spec = torch.load(spec_filename)
-        else:
-            spec = spectrogram_torch(audio_norm, self.filter_length,
-                self.sampling_rate, self.hop_length, self.win_length,
-                center=False)
-            spec = torch.squeeze(spec, 0)
-            torch.save(spec, spec_filename)
-        return spec, audio_norm
-
-    def get_text(self, text):
-        if self.cleaned_text:
-            text_norm = cleaned_text_to_sequence(text)
-        else:
-            text_norm = text_to_sequence(text, self.text_cleaners)
-        if self.add_blank:
-            text_norm = commons.intersperse(text_norm, 0)
-        text_norm = torch.LongTensor(text_norm)
-        return text_norm
-
-    def __getitem__(self, index):
-        return self.get_audio_text_pair(self.audiopaths_and_text[index])
-
-    def __len__(self):
-        return len(self.audiopaths_and_text)
-
-
-class TextAudioCollate():
-    """ Zero-pads model inputs and targets
-    """
-    def __init__(self, return_ids=False):
-        self.return_ids = return_ids
-
-    def __call__(self, batch):
-        """Collate's training batch from normalized text and aduio
-        PARAMS
-        ------
-        batch: [text_normalized, spec_normalized, wav_normalized]
-        """
-        # Right zero-pad all one-hot text sequences to max input length
-        _, ids_sorted_decreasing = torch.sort(
-            torch.LongTensor([x[1].size(1) for x in batch]),
-            dim=0, descending=True)
-
-        max_text_len = max([len(x[0]) for x in batch])
-        max_spec_len = max([x[1].size(1) for x in batch])
-        max_wav_len = max([x[2].size(1) for x in batch])
-
-        text_lengths = torch.LongTensor(len(batch))
-        spec_lengths = torch.LongTensor(len(batch))
-        wav_lengths = torch.LongTensor(len(batch))
-
-        text_padded = torch.LongTensor(len(batch), max_text_len)
-        spec_padded = torch.FloatTensor(len(batch), batch[0][1].size(0), max_spec_len)
-        wav_padded = torch.FloatTensor(len(batch), 1, max_wav_len)
-        text_padded.zero_()
-        spec_padded.zero_()
-        wav_padded.zero_()
-        for i in range(len(ids_sorted_decreasing)):
-            row = batch[ids_sorted_decreasing[i]]
-
-            text = row[0]
-            text_padded[i, :text.size(0)] = text
-            text_lengths[i] = text.size(0)
-
-            spec = row[1]
-            spec_padded[i, :, :spec.size(1)] = spec
-            spec_lengths[i] = spec.size(1)
-
-            wav = row[2]
-            wav_padded[i, :, :wav.size(1)] = wav
-            wav_lengths[i] = wav.size(1)
-
-        if self.return_ids:
-            return text_padded, text_lengths, spec_padded, spec_lengths, wav_padded, wav_lengths, ids_sorted_decreasing
-        return text_padded, text_lengths, spec_padded, spec_lengths, wav_padded, wav_lengths
-
-
-"""Multi speaker version"""
-class TextAudioSpeakerLoader(torch.utils.data.Dataset):
-    """
-        1) loads audio, speaker_id, text pairs
-        2) normalizes text and converts them to sequences of integers
-        3) computes spectrograms from audio files.
-    """
-    def __init__(self, audiopaths_sid_text, hparams):
-        self.audiopaths_sid_text = load_filepaths_and_text(audiopaths_sid_text)
-        self.text_cleaners = hparams.text_cleaners
-        self.max_wav_value = hparams.max_wav_value
-        self.sampling_rate = hparams.sampling_rate
-        self.filter_length  = hparams.filter_length
-        self.hop_length     = hparams.hop_length
-        self.win_length     = hparams.win_length
-        self.sampling_rate  = hparams.sampling_rate
-
-        self.cleaned_text = getattr(hparams, "cleaned_text", False)
-
-        self.add_blank = hparams.add_blank
-        self.min_text_len = getattr(hparams, "min_text_len", 1)
-        self.max_text_len = getattr(hparams, "max_text_len", 190)
-
-        random.seed(1234)
-        random.shuffle(self.audiopaths_sid_text)
-        self._filter()
-
-    def _filter(self):
-        """
-        Filter text & store spec lengths
-        """
-        # Store spectrogram lengths for Bucketing
-        # wav_length ~= file_size / (wav_channels * Bytes per dim) = file_size / (1 * 2)
-        # spec_length = wav_length // hop_length
-
-        audiopaths_sid_text_new = []
-        lengths = []
-        for audiopath, sid, text in self.audiopaths_sid_text:
-            if self.min_text_len <= len(text) and len(text) <= self.max_text_len:
-                audiopaths_sid_text_new.append([audiopath, sid, text])
-                lengths.append(os.path.getsize(audiopath) // (2 * self.hop_length))
-        self.audiopaths_sid_text = audiopaths_sid_text_new
-        self.lengths = lengths
-
-    def get_audio_text_speaker_pair(self, audiopath_sid_text):
-        # separate filename, speaker_id and text
-        audiopath, sid, text = audiopath_sid_text[0], audiopath_sid_text[1], audiopath_sid_text[2]
-        text = self.get_text(text)
-        spec, wav = self.get_audio(audiopath)
-        sid = self.get_sid(sid)
-        return (text, spec, wav, sid)
-
-    def get_audio(self, filename):
-        audio, sampling_rate = load_wav_to_torch(filename)
-        if sampling_rate != self.sampling_rate:
-            raise ValueError("{} {} SR doesn't match target {} SR".format(
-                sampling_rate, self.sampling_rate))
-        audio_norm = audio / self.max_wav_value
-        audio_norm = audio_norm.unsqueeze(0)
-        spec_filename = filename.replace(".wav", ".spec.pt")
-        if os.path.exists(spec_filename):
-            spec = torch.load(spec_filename)
-        else:
-            spec = spectrogram_torch(audio_norm, self.filter_length,
-                self.sampling_rate, self.hop_length, self.win_length,
-                center=False)
-            spec = torch.squeeze(spec, 0)
-            torch.save(spec, spec_filename)
-        return spec, audio_norm
-
-    def get_text(self, text):
-        if self.cleaned_text:
-            text_norm = cleaned_text_to_sequence(text)
-        else:
-            text_norm = text_to_sequence(text, self.text_cleaners)
-        if self.add_blank:
-            text_norm = commons.intersperse(text_norm, 0)
-        text_norm = torch.LongTensor(text_norm)
-        return text_norm
-
-    def get_sid(self, sid):
-        sid = torch.LongTensor([int(sid)])
-        return sid
-
-    def __getitem__(self, index):
-        return self.get_audio_text_speaker_pair(self.audiopaths_sid_text[index])
-
-    def __len__(self):
-        return len(self.audiopaths_sid_text)
-
-
-class TextAudioSpeakerCollate():
-    """ Zero-pads model inputs and targets
-    """
-    def __init__(self, return_ids=False):
-        self.return_ids = return_ids
-
-    def __call__(self, batch):
-        """Collate's training batch from normalized text, audio and speaker identities
-        PARAMS
-        ------
-        batch: [text_normalized, spec_normalized, wav_normalized, sid]
-        """
-        # Right zero-pad all one-hot text sequences to max input length
-        _, ids_sorted_decreasing = torch.sort(
-            torch.LongTensor([x[1].size(1) for x in batch]),
-            dim=0, descending=True)
-
-        max_text_len = max([len(x[0]) for x in batch])
-        max_spec_len = max([x[1].size(1) for x in batch])
-        max_wav_len = max([x[2].size(1) for x in batch])
-
-        text_lengths = torch.LongTensor(len(batch))
-        spec_lengths = torch.LongTensor(len(batch))
-        wav_lengths = torch.LongTensor(len(batch))
-        sid = torch.LongTensor(len(batch))
-
-        text_padded = torch.LongTensor(len(batch), max_text_len)
-        spec_padded = torch.FloatTensor(len(batch), batch[0][1].size(0), max_spec_len)
-        wav_padded = torch.FloatTensor(len(batch), 1, max_wav_len)
-        text_padded.zero_()
-        spec_padded.zero_()
-        wav_padded.zero_()
-        for i in range(len(ids_sorted_decreasing)):
-            row = batch[ids_sorted_decreasing[i]]
-
-            text = row[0]
-            text_padded[i, :text.size(0)] = text
-            text_lengths[i] = text.size(0)
-
-            spec = row[1]
-            spec_padded[i, :, :spec.size(1)] = spec
-            spec_lengths[i] = spec.size(1)
-
-            wav = row[2]
-            wav_padded[i, :, :wav.size(1)] = wav
-            wav_lengths[i] = wav.size(1)
-
-            sid[i] = row[3]
-
-        if self.return_ids:
-            return text_padded, text_lengths, spec_padded, spec_lengths, wav_padded, wav_lengths, sid, ids_sorted_decreasing
-        return text_padded, text_lengths, spec_padded, spec_lengths, wav_padded, wav_lengths, sid
-
-
-class DistributedBucketSampler(torch.utils.data.distributed.DistributedSampler):
-    """
-    Maintain similar input lengths in a batch.
-    Length groups are specified by boundaries.
-    Ex) boundaries = [b1, b2, b3] -> any batch is included either {x | b1 < length(x) <=b2} or {x | b2 < length(x) <= b3}.
-  
-    It removes samples which are not included in the boundaries.
-    Ex) boundaries = [b1, b2, b3] -> any x s.t. length(x) <= b1 or length(x) > b3 are discarded.
-    """
-    def __init__(self, dataset, batch_size, boundaries, num_replicas=None, rank=None, shuffle=True):
-        super().__init__(dataset, num_replicas=num_replicas, rank=rank, shuffle=shuffle)
-        self.lengths = dataset.lengths
-        self.batch_size = batch_size
-        self.boundaries = boundaries
-  
-        self.buckets, self.num_samples_per_bucket = self._create_buckets()
-        self.total_size = sum(self.num_samples_per_bucket)
-        self.num_samples = self.total_size // self.num_replicas
-  
-    def _create_buckets(self):
-        buckets = [[] for _ in range(len(self.boundaries) - 1)]
-        for i in range(len(self.lengths)):
-            length = self.lengths[i]
-            idx_bucket = self._bisect(length)
-            if idx_bucket != -1:
-                buckets[idx_bucket].append(i)
-  
-        for i in range(len(buckets) - 1, 0, -1):
-            if len(buckets[i]) == 0:
-                buckets.pop(i)
-                self.boundaries.pop(i+1)
-  
-        num_samples_per_bucket = []
-        for i in range(len(buckets)):
-            len_bucket = len(buckets[i])
-            total_batch_size = self.num_replicas * self.batch_size
-            rem = (total_batch_size - (len_bucket % total_batch_size)) % total_batch_size
-            num_samples_per_bucket.append(len_bucket + rem)
-        return buckets, num_samples_per_bucket
-  
-    def __iter__(self):
-      # deterministically shuffle based on epoch
-      g = torch.Generator()
-      g.manual_seed(self.epoch)
-  
-      indices = []
-      if self.shuffle:
-          for bucket in self.buckets:
-              indices.append(torch.randperm(len(bucket), generator=g).tolist())
-      else:
-          for bucket in self.buckets:
-              indices.append(list(range(len(bucket))))
-  
-      batches = []
-      for i in range(len(self.buckets)):
-          bucket = self.buckets[i]
-          len_bucket = len(bucket)
-          ids_bucket = indices[i]
-          num_samples_bucket = self.num_samples_per_bucket[i]
-  
-          # add extra samples to make it evenly divisible
-          rem = num_samples_bucket - len_bucket
-          ids_bucket = ids_bucket + ids_bucket * (rem // len_bucket) + ids_bucket[:(rem % len_bucket)]
-  
-          # subsample
-          ids_bucket = ids_bucket[self.rank::self.num_replicas]
-  
-          # batching
-          for j in range(len(ids_bucket) // self.batch_size):
-              batch = [bucket[idx] for idx in ids_bucket[j*self.batch_size:(j+1)*self.batch_size]]
-              batches.append(batch)
-  
-      if self.shuffle:
-          batch_ids = torch.randperm(len(batches), generator=g).tolist()
-          batches = [batches[i] for i in batch_ids]
-      self.batches = batches
-  
-      assert len(self.batches) * self.batch_size == self.num_samples
-      return iter(self.batches)
-  
-    def _bisect(self, x, lo=0, hi=None):
-      if hi is None:
-          hi = len(self.boundaries) - 1
-  
-      if hi > lo:
-          mid = (hi + lo) // 2
-          if self.boundaries[mid] < x and x <= self.boundaries[mid+1]:
-              return mid
-          elif x <= self.boundaries[mid]:
-              return self._bisect(x, lo, mid)
-          else:
-              return self._bisect(x, mid + 1, hi)
-      else:
-          return -1
-
-    def __len__(self):
-        return self.num_samples // self.batch_size

losses.py

@@ -1,8 +1,4 @@
 import torch 
-from torch.nn import functional as F
-
-import commons
-
 
 def feature_loss(fmap_r, fmap_g):
   loss = 0

mel_processing.py

@@ -1,21 +1,9 @@
-import math
-import os
-import random
 import torch
-from torch import nn
-import torch.nn.functional as F
 import torch.utils.data
-import numpy as np
-import librosa
-import librosa.util as librosa_util
-from librosa.util import normalize, pad_center, tiny
-from scipy.signal import get_window
-from scipy.io.wavfile import read
 from librosa.filters import mel as librosa_mel_fn
 
 MAX_WAV_VALUE = 32768.0
 
-
 def dynamic_range_compression_torch(x, C=1, clip_val=1e-5):
     """
     PARAMS

modules.py

@@ -1,7 +1,6 @@
 import copy
 import math
 import numpy as np
-import scipy
 import torch
 from torch import nn
 from torch.nn import functional as F

preprocess.py

@@ -1,25 +0,0 @@
-import argparse
-import text
-from utils import load_filepaths_and_text
-
-if __name__ == '__main__':
-  parser = argparse.ArgumentParser()
-  parser.add_argument("--out_extension", default="cleaned")
-  parser.add_argument("--text_index", default=1, type=int)
-  parser.add_argument("--filelists", nargs="+", default=["filelists/ljs_audio_text_val_filelist.txt", "filelists/ljs_audio_text_test_filelist.txt"])
-  parser.add_argument("--text_cleaners", nargs="+", default=["english_cleaners2"])
-
-  args = parser.parse_args()
-    
-
-  for filelist in args.filelists:
-    print("START:", filelist)
-    filepaths_and_text = load_filepaths_and_text(filelist)
-    for i in range(len(filepaths_and_text)):
-      original_text = filepaths_and_text[i][args.text_index]
-      cleaned_text = text._clean_text(original_text, args.text_cleaners)
-      filepaths_and_text[i][args.text_index] = cleaned_text
-
-    new_filelist = filelist + "." + args.out_extension
-    with open(new_filelist, "w", encoding="utf-8") as f:
-      f.writelines(["|".join(x) + "\n" for x in filepaths_and_text])