1. using sentencepiece for text_to_seq

2. using 40 mel channels
3. added makefile and .gitignore

.gitignore

@@ -0,0 +1,145 @@
+.env
+env/
+jupyter.json
+# Created by https://www.gitignore.io/api/macos
+# Edit at https://www.gitignore.io/?templates=macos
+
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+# End of https://www.gitignore.io/api/macos
+
+# Created by https://www.gitignore.io/api/python
+# Edit at https://www.gitignore.io/?templates=python
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# Mr Developer
+.mr.developer.cfg
+.project
+.pydevproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# End of https://www.gitignore.io/api/python

Makefile

@@ -0,0 +1,6 @@
+.PHONY: clean clean-test clean-pyc clean-build docs help common.mk
+.DEFAULT_GOAL := help
+
+
+notebook:
+	jupyter lab --ip=0.0.0.0 --no-browser --NotebookApp.token='${JUPYTER_TOKEN}'

common.mk

@@ -0,0 +1,27 @@
+define BROWSER_PYSCRIPT
+import os, webbrowser, sys
+
+try:
+	from urllib import pathname2url
+except:
+	from urllib.request import pathname2url
+
+webbrowser.open("file://" + pathname2url(os.path.abspath(sys.argv[1])))
+endef
+export BROWSER_PYSCRIPT
+
+define PRINT_HELP_PYSCRIPT
+import re, sys
+
+for line in sys.stdin:
+	match = re.match(r'^([a-zA-Z_-]+):.*?## (.*)$$', line)
+	if match:
+		target, help = match.groups()
+		print("%-20s %s" % (target, help))
+endef
+export PRINT_HELP_PYSCRIPT
+
+BROWSER := python -c "$$BROWSER_PYSCRIPT"
+
+help:  ##  make TARGET forwards the TARGET to sub packages
+	@cat $(MAKEFILE_LIST) | python -c "$$PRINT_HELP_PYSCRIPT"

data_utils.py

@@ -5,8 +5,8 @@ import torch.utils.data
 
 import layers
 from utils import load_wav_to_torch, load_filepaths_and_text
-from text import text_to_sequence
-
+# from text import text_to_sequence
+from spm_codec import text_to_sequence
 
 class TextMelLoader(torch.utils.data.Dataset):
     """

hparams.py

@@ -37,7 +37,7 @@ def create_hparams(hparams_string=None, verbose=False):
         filter_length=1024,
         hop_length=256,
         win_length=1024,
-        n_mel_channels=80,
+        n_mel_channels=40,
         mel_fmin=0.0,
         mel_fmax=8000.0,
 

spm_codec.py

@@ -0,0 +1,65 @@
+from utils import load_filepaths_and_text
+
+# from text import text_to_sequence, sequence_to_text
+
+from hparams import create_hparams
+import sentencepiece as spm
+from text import symbols
+
+
+SPM_CORPUS_FILE = "filelists/text_corpus.txt"
+SPM_MODEL_PREFIX = "spm"
+SPM_VOCAB_SIZE = 1000
+hparams = create_hparams()
+
+
+def _create_sentencepiece_corpus():
+    def get_text_list(text_file):
+        return [i[1] + "\n" for i in load_filepaths_and_text(text_file)]
+
+    full_text_list = get_text_list(hparams.training_files) + get_text_list(
+        hparams.validation_files
+    )
+    with open(SPM_CORPUS_FILE, "w") as fd:
+        fd.writelines(full_text_list)
+
+
+def _create_sentencepiece_vocab(vocab_size=SPM_VOCAB_SIZE):
+    train_params = "--input={} --model_prefix={} --vocab_size={}".format(
+        SPM_CORPUS_FILE, SPM_MODEL_PREFIX, vocab_size
+    )
+    spm.SentencePieceTrainer.Train(train_params)
+
+
+def _spm_text_codecs():
+    sp = spm.SentencePieceProcessor()
+    sp.Load("{}.model".format(SPM_MODEL_PREFIX))
+
+    def ttseq(text, cleaners):
+        return sp.EncodeAsIds(text)
+
+    def seqtt(sequence):
+        return sp.DecodeIds(sequence)
+
+    return ttseq, seqtt
+
+
+text_to_sequence, sequence_to_text = _spm_text_codecs()
+
+
+def _interactive_test():
+    prompt = "Hello world; how are you, doing ?"
+    while prompt not in ["q", "quit"]:
+        oup = sequence_to_text(text_to_sequence(prompt, hparams.text_cleaners))
+        print('==> ',oup)
+        prompt = input("> ")
+
+
+def main():
+    # _create_sentencepiece_corpus()
+    # _create_sentencepiece_vocab()
+    _interactive_test()
+
+
+if __name__ == "__main__":
+    main()