First

.env.example

@@ -0,0 +1,6 @@
+# example of file for storing private and user specific environment variables, like keys or system paths
+# rename it to ".env" (excluded from version control by default)
+# .env is loaded by train.py automatically
+# hydra allows you to reference variables in .yaml configs with special syntax: ${oc.env:MY_VAR}
+
+MY_VAR="/home/user/my/system/path"

.gitattributes

@@ -1,35 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,163 @@
+# 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
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# 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
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+### VisualStudioCode
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+*.code-workspace
+**/.vscode
+
+# JetBrains
+.idea/
+
+# Data & Models
+*.h5
+*.tar
+*.tar.gz
+
+# Lightning-Hydra-Template
+configs/local/default.yaml
+/data/
+/logs/
+.env
+
+# Aim logging
+.aim
+
+# Cython complied files
+matcha/utils/monotonic_align/core.c
+
+# Ignoring hifigan checkpoint
+generator_v1
+g_02500000
+gradio_cached_examples/
+synth_output/

.pre-commit-config.yaml

@@ -0,0 +1,59 @@
+default_language_version:
+  python: python3.10
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      # list of supported hooks: https://pre-commit.com/hooks.html
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      # - id: check-docstring-first
+      - id: check-yaml
+      - id: debug-statements
+      - id: detect-private-key
+      - id: check-toml
+      - id: check-case-conflict
+      - id: check-added-large-files
+
+  # python code formatting
+  - repo: https://github.com/psf/black
+    rev: 23.12.1
+    hooks:
+      - id: black
+        args: [--line-length, "120"]
+
+  # python import sorting
+  - repo: https://github.com/PyCQA/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort
+        args: ["--profile", "black", "--filter-files"]
+
+  # python upgrading syntax to newer version
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v3.15.0
+    hooks:
+      - id: pyupgrade
+        args: [--py38-plus]
+
+  # python check (PEP8), programming errors and code complexity
+  - repo: https://github.com/PyCQA/flake8
+    rev: 7.0.0
+    hooks:
+      - id: flake8
+        args:
+          [
+            "--max-line-length", "120",
+            "--extend-ignore",
+            "E203,E402,E501,F401,F841,RST2,RST301",
+            "--exclude",
+            "logs/*,data/*,matcha/hifigan/*",
+          ]
+        additional_dependencies: [flake8-rst-docstrings==0.3.0]
+
+  # pylint
+  - repo: https://github.com/pycqa/pylint
+    rev: v3.0.3
+    hooks:
+    -   id: pylint

.project-root

@@ -0,0 +1,2 @@
+# this file is required for inferring the project root directory
+# do not delete

.pylintrc

@@ -0,0 +1,525 @@
+[MASTER]
+
+# A comma-separated list of package or module names from where C extensions may
+# be loaded. Extensions are loading into the active Python interpreter and may
+# run arbitrary code.
+extension-pkg-whitelist=
+
+# Add files or directories to the blacklist. They should be base names, not
+# paths.
+ignore=CVS
+
+# Add files or directories matching the regex patterns to the blacklist. The
+# regex matches against base names, not paths.
+ignore-patterns=
+
+# Python code to execute, usually for sys.path manipulation such as
+# pygtk.require().
+#init-hook=
+
+# Use multiple processes to speed up Pylint. Specifying 0 will auto-detect the
+# number of processors available to use.
+jobs=1
+
+# Control the amount of potential inferred values when inferring a single
+# object. This can help the performance when dealing with large functions or
+# complex, nested conditions.
+limit-inference-results=100
+
+# List of plugins (as comma separated values of python modules names) to load,
+# usually to register additional checkers.
+load-plugins=
+
+# Pickle collected data for later comparisons.
+persistent=yes
+
+# Specify a configuration file.
+#rcfile=
+
+# When enabled, pylint would attempt to guess common misconfiguration and emit
+# user-friendly hints instead of false-positive error messages.
+suggestion-mode=yes
+
+# Allow loading of arbitrary C extensions. Extensions are imported into the
+# active Python interpreter and may run arbitrary code.
+unsafe-load-any-extension=no
+
+
+[MESSAGES CONTROL]
+
+# Only show warnings with the listed confidence levels. Leave empty to show
+# all. Valid levels: HIGH, INFERENCE, INFERENCE_FAILURE, UNDEFINED.
+confidence=
+
+# Disable the message, report, category or checker with the given id(s). You
+# can either give multiple identifiers separated by comma (,) or put this
+# option multiple times (only on the command line, not in the configuration
+# file where it should appear only once). You can also use "--disable=all" to
+# disable everything first and then reenable specific checks. For example, if
+# you want to run only the similarities checker, you can use "--disable=all
+# --enable=similarities". If you want to run only the classes checker, but have
+# no Warning level messages displayed, use "--disable=all --enable=classes
+# --disable=W".
+disable=missing-docstring,
+        too-many-public-methods,
+        too-many-lines,
+        bare-except,
+        ## for avoiding weird p3.6 CI linter error
+        ## TODO: see later if we can remove this
+        assigning-non-slot,
+        unsupported-assignment-operation,
+        ## end
+        line-too-long,
+        fixme,
+        wrong-import-order,
+        ungrouped-imports,
+        wrong-import-position,
+        import-error,
+        invalid-name,
+        too-many-instance-attributes,
+        arguments-differ,
+        arguments-renamed,
+        no-name-in-module,
+        no-member,
+        unsubscriptable-object,
+        raw-checker-failed,
+        bad-inline-option,
+        locally-disabled,
+        file-ignored,
+        suppressed-message,
+        useless-suppression,
+        deprecated-pragma,
+        use-symbolic-message-instead,
+        useless-object-inheritance,
+        too-few-public-methods,
+        too-many-branches,
+        too-many-arguments,
+        too-many-locals,
+        too-many-statements,
+        duplicate-code,
+        not-callable,
+        import-outside-toplevel,
+        logging-fstring-interpolation,
+        logging-not-lazy,
+        unused-argument,
+        no-else-return,
+        chained-comparison,
+        redefined-outer-name
+
+# Enable the message, report, category or checker with the given id(s). You can
+# either give multiple identifier separated by comma (,) or put this option
+# multiple time (only on the command line, not in the configuration file where
+# it should appear only once). See also the "--disable" option for examples.
+enable=c-extension-no-member
+
+
+[REPORTS]
+
+# Python expression which should return a note less than 10 (10 is the highest
+# note). You have access to the variables errors warning, statement which
+# respectively contain the number of errors / warnings messages and the total
+# number of statements analyzed. This is used by the global evaluation report
+# (RP0004).
+evaluation=10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10)
+
+# Template used to display messages. This is a python new-style format string
+# used to format the message information. See doc for all details.
+#msg-template=
+
+# Set the output format. Available formats are text, parseable, colorized, json
+# and msvs (visual studio). You can also give a reporter class, e.g.
+# mypackage.mymodule.MyReporterClass.
+output-format=text
+
+# Tells whether to display a full report or only the messages.
+reports=no
+
+# Activate the evaluation score.
+score=yes
+
+
+[REFACTORING]
+
+# Maximum number of nested blocks for function / method body
+max-nested-blocks=5
+
+# Complete name of functions that never returns. When checking for
+# inconsistent-return-statements if a never returning function is called then
+# it will be considered as an explicit return statement and no message will be
+# printed.
+never-returning-functions=sys.exit
+
+
+[LOGGING]
+
+# Format style used to check logging format string. `old` means using %
+# formatting, while `new` is for `{}` formatting.
+logging-format-style=old
+
+# Logging modules to check that the string format arguments are in logging
+# function parameter format.
+logging-modules=logging
+
+
+[SPELLING]
+
+# Limits count of emitted suggestions for spelling mistakes.
+max-spelling-suggestions=4
+
+# Spelling dictionary name. Available dictionaries: none. To make it working
+# install python-enchant package..
+spelling-dict=
+
+# List of comma separated words that should not be checked.
+spelling-ignore-words=
+
+# A path to a file that contains private dictionary; one word per line.
+spelling-private-dict-file=
+
+# Tells whether to store unknown words to indicated private dictionary in
+# --spelling-private-dict-file option instead of raising a message.
+spelling-store-unknown-words=no
+
+
+[MISCELLANEOUS]
+
+# List of note tags to take in consideration, separated by a comma.
+notes=FIXME,
+      XXX,
+      TODO
+
+
+[TYPECHECK]
+
+# List of decorators that produce context managers, such as
+# contextlib.contextmanager. Add to this list to register other decorators that
+# produce valid context managers.
+contextmanager-decorators=contextlib.contextmanager
+
+# List of members which are set dynamically and missed by pylint inference
+# system, and so shouldn't trigger E1101 when accessed. Python regular
+# expressions are accepted.
+generated-members=numpy.*,torch.*
+
+# Tells whether missing members accessed in mixin class should be ignored. A
+# mixin class is detected if its name ends with "mixin" (case insensitive).
+ignore-mixin-members=yes
+
+# Tells whether to warn about missing members when the owner of the attribute
+# is inferred to be None.
+ignore-none=yes
+
+# This flag controls whether pylint should warn about no-member and similar
+# checks whenever an opaque object is returned when inferring. The inference
+# can return multiple potential results while evaluating a Python object, but
+# some branches might not be evaluated, which results in partial inference. In
+# that case, it might be useful to still emit no-member and other checks for
+# the rest of the inferred objects.
+ignore-on-opaque-inference=yes
+
+# List of class names for which member attributes should not be checked (useful
+# for classes with dynamically set attributes). This supports the use of
+# qualified names.
+ignored-classes=optparse.Values,thread._local,_thread._local
+
+# List of module names for which member attributes should not be checked
+# (useful for modules/projects where namespaces are manipulated during runtime
+# and thus existing member attributes cannot be deduced by static analysis. It
+# supports qualified module names, as well as Unix pattern matching.
+ignored-modules=
+
+# Show a hint with possible names when a member name was not found. The aspect
+# of finding the hint is based on edit distance.
+missing-member-hint=yes
+
+# The minimum edit distance a name should have in order to be considered a
+# similar match for a missing member name.
+missing-member-hint-distance=1
+
+# The total number of similar names that should be taken in consideration when
+# showing a hint for a missing member.
+missing-member-max-choices=1
+
+
+[VARIABLES]
+
+# List of additional names supposed to be defined in builtins. Remember that
+# you should avoid defining new builtins when possible.
+additional-builtins=
+
+# Tells whether unused global variables should be treated as a violation.
+allow-global-unused-variables=yes
+
+# List of strings which can identify a callback function by name. A callback
+# name must start or end with one of those strings.
+callbacks=cb_,
+          _cb
+
+# A regular expression matching the name of dummy variables (i.e. expected to
+# not be used).
+dummy-variables-rgx=_+$|(_[a-zA-Z0-9_]*[a-zA-Z0-9]+?$)|dummy|^ignored_|^unused_
+
+# Argument names that match this expression will be ignored. Default to name
+# with leading underscore.
+ignored-argument-names=_.*|^ignored_|^unused_
+
+# Tells whether we should check for unused import in __init__ files.
+init-import=no
+
+# List of qualified module names which can have objects that can redefine
+# builtins.
+redefining-builtins-modules=six.moves,past.builtins,future.builtins,builtins,io
+
+
+[FORMAT]
+
+# Expected format of line ending, e.g. empty (any line ending), LF or CRLF.
+expected-line-ending-format=
+
+# Regexp for a line that is allowed to be longer than the limit.
+ignore-long-lines=^\s*(# )?<?https?://\S+>?$
+
+# Number of spaces of indent required inside a hanging or continued line.
+indent-after-paren=4
+
+# String used as indentation unit. This is usually "    " (4 spaces) or "\t" (1
+# tab).
+indent-string='    '
+
+# Maximum number of characters on a single line.
+max-line-length=120
+
+# Maximum number of lines in a module.
+max-module-lines=1000
+
+# Allow the body of a class to be on the same line as the declaration if body
+# contains single statement.
+single-line-class-stmt=no
+
+# Allow the body of an if to be on the same line as the test if there is no
+# else.
+single-line-if-stmt=no
+
+
+[SIMILARITIES]
+
+# Ignore comments when computing similarities.
+ignore-comments=yes
+
+# Ignore docstrings when computing similarities.
+ignore-docstrings=yes
+
+# Ignore imports when computing similarities.
+ignore-imports=no
+
+# Minimum lines number of a similarity.
+min-similarity-lines=4
+
+
+[BASIC]
+
+# Naming style matching correct argument names.
+argument-naming-style=snake_case
+
+# Regular expression matching correct argument names. Overrides argument-
+# naming-style.
+argument-rgx=[a-z_][a-z0-9_]{0,30}$
+
+# Naming style matching correct attribute names.
+attr-naming-style=snake_case
+
+# Regular expression matching correct attribute names. Overrides attr-naming-
+# style.
+#attr-rgx=
+
+# Bad variable names which should always be refused, separated by a comma.
+bad-names=
+
+# Naming style matching correct class attribute names.
+class-attribute-naming-style=any
+
+# Regular expression matching correct class attribute names. Overrides class-
+# attribute-naming-style.
+#class-attribute-rgx=
+
+# Naming style matching correct class names.
+class-naming-style=PascalCase
+
+# Regular expression matching correct class names. Overrides class-naming-
+# style.
+#class-rgx=
+
+# Naming style matching correct constant names.
+const-naming-style=UPPER_CASE
+
+# Regular expression matching correct constant names. Overrides const-naming-
+# style.
+#const-rgx=
+
+# Minimum line length for functions/classes that require docstrings, shorter
+# ones are exempt.
+docstring-min-length=-1
+
+# Naming style matching correct function names.
+function-naming-style=snake_case
+
+# Regular expression matching correct function names. Overrides function-
+# naming-style.
+#function-rgx=
+
+# Good variable names which should always be accepted, separated by a comma.
+good-names=i,
+           j,
+           k,
+           x,
+           ex,
+           Run,
+           _
+
+# Include a hint for the correct naming format with invalid-name.
+include-naming-hint=no
+
+# Naming style matching correct inline iteration names.
+inlinevar-naming-style=any
+
+# Regular expression matching correct inline iteration names. Overrides
+# inlinevar-naming-style.
+#inlinevar-rgx=
+
+# Naming style matching correct method names.
+method-naming-style=snake_case
+
+# Regular expression matching correct method names. Overrides method-naming-
+# style.
+#method-rgx=
+
+# Naming style matching correct module names.
+module-naming-style=snake_case
+
+# Regular expression matching correct module names. Overrides module-naming-
+# style.
+#module-rgx=
+
+# Colon-delimited sets of names that determine each other's naming style when
+# the name regexes allow several styles.
+name-group=
+
+# Regular expression which should only match function or class names that do
+# not require a docstring.
+no-docstring-rgx=^_
+
+# List of decorators that produce properties, such as abc.abstractproperty. Add
+# to this list to register other decorators that produce valid properties.
+# These decorators are taken in consideration only for invalid-name.
+property-classes=abc.abstractproperty
+
+# Naming style matching correct variable names.
+variable-naming-style=snake_case
+
+# Regular expression matching correct variable names. Overrides variable-
+# naming-style.
+variable-rgx=[a-z_][a-z0-9_]{0,30}$
+
+
+[STRING]
+
+# This flag controls whether the implicit-str-concat-in-sequence should
+# generate a warning on implicit string concatenation in sequences defined over
+# several lines.
+check-str-concat-over-line-jumps=no
+
+
+[IMPORTS]
+
+# Allow wildcard imports from modules that define __all__.
+allow-wildcard-with-all=no
+
+# Analyse import fallback blocks. This can be used to support both Python 2 and
+# 3 compatible code, which means that the block might have code that exists
+# only in one or another interpreter, leading to false positives when analysed.
+analyse-fallback-blocks=no
+
+# Deprecated modules which should not be used, separated by a comma.
+deprecated-modules=optparse,tkinter.tix
+
+# Create a graph of external dependencies in the given file (report RP0402 must
+# not be disabled).
+ext-import-graph=
+
+# Create a graph of every (i.e. internal and external) dependencies in the
+# given file (report RP0402 must not be disabled).
+import-graph=
+
+# Create a graph of internal dependencies in the given file (report RP0402 must
+# not be disabled).
+int-import-graph=
+
+# Force import order to recognize a module as part of the standard
+# compatibility libraries.
+known-standard-library=
+
+# Force import order to recognize a module as part of a third party library.
+known-third-party=enchant
+
+
+[CLASSES]
+
+# List of method names used to declare (i.e. assign) instance attributes.
+defining-attr-methods=__init__,
+                      __new__,
+                      setUp
+
+# List of member names, which should be excluded from the protected access
+# warning.
+exclude-protected=_asdict,
+                  _fields,
+                  _replace,
+                  _source,
+                  _make
+
+# List of valid names for the first argument in a class method.
+valid-classmethod-first-arg=cls
+
+# List of valid names for the first argument in a metaclass class method.
+valid-metaclass-classmethod-first-arg=cls
+
+
+[DESIGN]
+
+# Maximum number of arguments for function / method.
+max-args=5
+
+# Maximum number of attributes for a class (see R0902).
+max-attributes=7
+
+# Maximum number of boolean expressions in an if statement.
+max-bool-expr=5
+
+# Maximum number of branch for function / method body.
+max-branches=12
+
+# Maximum number of locals for function / method body.
+max-locals=15
+
+# Maximum number of parents for a class (see R0901).
+max-parents=15
+
+# Maximum number of public methods for a class (see R0904).
+max-public-methods=20
+
+# Maximum number of return / yield for function / method body.
+max-returns=6
+
+# Maximum number of statements in function / method body.
+max-statements=50
+
+# Minimum number of public methods for a class (see R0903).
+min-public-methods=2
+
+
+[EXCEPTIONS]
+
+# Exceptions that will emit a warning when being caught. Defaults to
+# "BaseException, Exception".
+overgeneral-exceptions=builtins.BaseException,
+                       builtins.Exception

Create_dataset/__init__.py

@@ -0,0 +1 @@
+

Create_dataset/cr_dataset_script.py

@@ -0,0 +1,97 @@
+import pandas as pd
+import numpy as np
+from datasets import load_dataset
+from datasets import Dataset, DatasetDict
+from IPython.display import Audio
+import scipy
+import librosa
+from tqdm import tqdm
+import re
+import os
+
+
+def load_audio(audio_dict:dict)->None:
+  target_sr = 22050
+  audio_resampled = librosa.resample(np.array(audio_dict['array']),
+                                     orig_sr=audio_dict['sampling_rate'],
+                                     target_sr=target_sr)
+  scipy.io.wavfile.write(audio_dict['path'],
+                         rate=target_sr,
+                         data=(audio_resampled* 32767).astype(np.int16))
+
+def remove_outer_quotes_regex(sen:str)->str:
+  return re.sub(r'^["\'](.*)["\']$', r'\1', sen)
+
+def main()->None:
+  os.mkdir('kany_dataset')
+  os.chdir('kany_dataset')
+  os.mkdir('wavs')
+  os.chdir('wavs')
+
+
+  art = """
+            /\_/\ 
+           ( o.o ) 
+            > ^ <
+
+      V   O   I   C    E
+  """
+  print(art)
+  
+  print('--- LOADING DATASET ---')
+  dataset_kany = load_dataset("Simonlob/Kany_dataset_mk4")
+  
+  # mk TRAIN
+  print()
+  print('--- CONVERTIND AND SAVING THE TRAIN DATASET ---')
+  num_shards=20
+  path = []
+  text = []
+
+  with tqdm(total=len(dataset_kany['train']), leave=False) as pbar:
+    for ind in range(num_shards):
+      dataset_shard = dataset_kany['train'].shard(num_shards=num_shards, index=ind)
+      for row in dataset_shard:
+        load_audio(row['audio'])
+        path.append(row['audio']['path'])
+        text.append(row['raw_transcription'])
+        pbar.update(1)
+
+  
+  absolute_path = os.path.abspath('../')
+  os.chdir(absolute_path)
+  
+  dir = f'{absolute_path}/wavs/'
+  df = pd.DataFrame({'path':path, 'text':text})
+  df.text = df.text.map(remove_outer_quotes_regex)
+  df.path = dir + df.path
+  df.to_csv('kany_filelist_train.txt', sep='|', header=None, index=False)
+  
+  # mk TEST
+  os.chdir(dir)
+  path = []
+  text = []
+  print()
+  print('--- CONVERTIND AND SAVING THE TEST DATASET ---')
+  with tqdm(total=len(dataset_kany['test']), leave=False) as pbar2:
+    for row in tqdm(dataset_kany['test']):
+      load_audio(row['audio'])
+      path.append(row['audio']['path'])
+      text.append(row['raw_transcription'])
+      pbar2.update(1)
+  
+  os.chdir(absolute_path)
+  df = pd.DataFrame({'path':path, 'text':text})
+  df.text = df.text.map(remove_outer_quotes_regex)
+  df.path = dir + df.path
+  df.to_csv('kany_filelist_test.txt', sep='|', header=None, index=False)
+  print()
+  print('--- THE DATASET IS READY ---')
+  print(f'Dir of data is "{absolute_path}"')
+  
+  absolute_path_home = os.path.abspath('../')
+  os.chdir(absolute_path_home)
+
+
+if __name__ == "__main__":
+  main()

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Shivam Mehta
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

MANIFEST.in

@@ -0,0 +1,14 @@
+include README.md
+include LICENSE.txt
+include requirements.*.txt
+include *.cff
+include requirements.txt
+include matcha/VERSION
+recursive-include matcha *.json
+recursive-include matcha *.html
+recursive-include matcha *.png
+recursive-include matcha *.md
+recursive-include matcha *.py
+recursive-include matcha *.pyx
+recursive-exclude tests *
+prune tests*

Makefile

@@ -0,0 +1,42 @@
+
+help:  ## Show help
+	@grep -E '^[.a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}'
+
+clean: ## Clean autogenerated files
+	rm -rf dist
+	find . -type f -name "*.DS_Store" -ls -delete
+	find . | grep -E "(__pycache__|\.pyc|\.pyo)" | xargs rm -rf
+	find . | grep -E ".pytest_cache" | xargs rm -rf
+	find . | grep -E ".ipynb_checkpoints" | xargs rm -rf
+	rm -f .coverage
+
+clean-logs: ## Clean logs
+	rm -rf logs/**
+
+create-package: ## Create wheel and tar gz
+	rm -rf dist/
+	python setup.py bdist_wheel --plat-name=manylinux1_x86_64
+	python setup.py sdist
+	python -m twine upload  dist/* --verbose --skip-existing
+
+format: ## Run pre-commit hooks
+	pre-commit run -a
+
+sync: ## Merge changes from main branch to your current branch
+	git pull
+	git pull origin main
+
+test: ## Run not slow tests
+	pytest -k "not slow"
+
+test-full: ## Run all tests
+	pytest
+
+train-ljspeech: ## Train the model
+	python matcha/train.py experiment=ljspeech
+
+train-ljspeech-min: ## Train the model with minimum memory
+	python matcha/train.py experiment=ljspeech_min_memory
+
+start_app: ## Start the app
+	python matcha/app.py

README.md

@@ -1,13 +1,70 @@
----
-title: Akylai Tts Mini
-emoji: 📈
-colorFrom: gray
-colorTo: gray
-sdk: gradio
-sdk_version: 4.26.0
-app_file: app.py
-pinned: false
-license: apache-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+<div align="center">
+
+
+
+# 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
+
+### [Shivam Mehta](https://www.kth.se/profile/smehta), [Ruibo Tu](https://www.kth.se/profile/ruibo), [Jonas Beskow](https://www.kth.se/profile/beskow), [Éva Székely](https://www.kth.se/profile/szekely), and [Gustav Eje Henter](https://people.kth.se/~ghe/)
+
+[![python](https://img.shields.io/badge/-Python_3.10-blue?logo=python&logoColor=white)](https://www.python.org/downloads/release/python-3100/)
+[![pytorch](https://img.shields.io/badge/PyTorch_2.0+-ee4c2c?logo=pytorch&logoColor=white)](https://pytorch.org/get-started/locally/)
+[![lightning](https://img.shields.io/badge/-Lightning_2.0+-792ee5?logo=pytorchlightning&logoColor=white)](https://pytorchlightning.ai/)
+[![hydra](https://img.shields.io/badge/Config-Hydra_1.3-89b8cd)](https://hydra.cc/)
+[![black](https://img.shields.io/badge/Code%20Style-Black-black.svg?labelColor=gray)](https://black.readthedocs.io/en/stable/)
+[![isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)
+
+<p style="text-align: center;">
+  <img src="https://shivammehta25.github.io/Matcha-TTS/images/logo.png" height="128"/>
+</p>
+
+</div>
+
+
+
+# Matcha-TTS for Kyrgyz language
+
+## Train with Kany Dataset
+
+The training dataset has 7016 samples and 13 hours of speech. All settings for training have already been made.
+
+## Process by Terminal
+
+* **Load this repo and connect to HF**
+
+```
+git clone https://github.com/simonlobgromov/Matcha-TTS
+cd Matcha-TTS
+pip install -e .
+```
+!!!The environment will be restarted!!!
+
+Install this:
+
+```
+apt-get install espeak-ng
+```
+Connect to HF
+
+```
+git config --global credential.helper store
+huggingface-cli login
+```
+
+* **Load the Data**
+
+```
+create-dataset
+
+# If you see a cat, then everything is fine!
+```
+
+* **Train**
+
+```
+python matcha/train.py experiment=akylai
+```
+
+* **Checkpoints**
+
+Checkpoints will be saved in `./Matcha-TTS/logs/train/akylai/runs/<DATE>_<TIME>/checkpoints`. Unload them or select the last few checkpoints.
+

app.py

@@ -0,0 +1,320 @@
+import tempfile
+from argparse import Namespace
+from pathlib import Path
+
+import gradio as gr
+import soundfile as sf
+import torch
+
+from matcha.cli import (
+    MATCHA_URLS,
+    VOCODER_URLS,
+    assert_model_downloaded,
+    get_device,
+    load_matcha,
+    load_vocoder,
+    process_text,
+    to_waveform,
+)
+from matcha.utils.utils import get_user_data_dir, plot_tensor
+
+LOCATION = Path(get_user_data_dir())
+
+args = Namespace(
+    cpu=False,
+    model="matcha_vctk",
+    vocoder="hifigan_univ_v1",
+    spk=0,
+)
+
+CURRENTLY_LOADED_MODEL = args.model
+
+
+def MATCHA_TTS_LOC(x):
+    return LOCATION / f"{x}.ckpt"
+
+
+def VOCODER_LOC(x):
+    return LOCATION / f"{x}"
+
+
+LOGO_URL = "https://shivammehta25.github.io/Matcha-TTS/images/logo.png"
+RADIO_OPTIONS = {
+    "Multi Speaker (VCTK)": {
+        "model": "matcha_vctk",
+        "vocoder": "hifigan_univ_v1",
+    },
+    "Single Speaker (LJ Speech)": {
+        "model": "akyl_ai",
+        "vocoder": "hifigan_T2_v1",
+    },
+}
+
+# Ensure all the required models are downloaded
+assert_model_downloaded(MATCHA_TTS_LOC("akyl_ai"), MATCHA_URLS["akyl_ai"])
+assert_model_downloaded(VOCODER_LOC("hifigan_T2_v1"), VOCODER_URLS["hifigan_T2_v1"])
+assert_model_downloaded(MATCHA_TTS_LOC("matcha_vctk"), MATCHA_URLS["matcha_vctk"])
+assert_model_downloaded(VOCODER_LOC("hifigan_univ_v1"), VOCODER_URLS["hifigan_univ_v1"])
+
+device = get_device(args)
+
+# Load default model
+model = load_matcha(args.model, MATCHA_TTS_LOC(args.model), device)
+vocoder, denoiser = load_vocoder(args.vocoder, VOCODER_LOC(args.vocoder), device)
+
+
+def load_model(model_name, vocoder_name):
+    model = load_matcha(model_name, MATCHA_TTS_LOC(model_name), device)
+    vocoder, denoiser = load_vocoder(vocoder_name, VOCODER_LOC(vocoder_name), device)
+    return model, vocoder, denoiser
+
+
+def load_model_ui(model_type, textbox):
+    model_name, vocoder_name = RADIO_OPTIONS[model_type]["model"], RADIO_OPTIONS[model_type]["vocoder"]
+
+    global model, vocoder, denoiser, CURRENTLY_LOADED_MODEL  # pylint: disable=global-statement
+    if CURRENTLY_LOADED_MODEL != model_name:
+        model, vocoder, denoiser = load_model(model_name, vocoder_name)
+        CURRENTLY_LOADED_MODEL = model_name
+
+    if model_name == "matcha_ljspeech":
+        spk_slider = gr.update(visible=False, value=-1)
+        single_speaker_examples = gr.update(visible=True)
+        multi_speaker_examples = gr.update(visible=False)
+        length_scale = gr.update(value=0.95)
+    else:
+        spk_slider = gr.update(visible=True, value=0)
+        single_speaker_examples = gr.update(visible=False)
+        multi_speaker_examples = gr.update(visible=True)
+        length_scale = gr.update(value=0.85)
+
+    return (
+        textbox,
+        gr.update(interactive=True),
+        spk_slider,
+        single_speaker_examples,
+        multi_speaker_examples,
+        length_scale,
+    )
+
+
+@torch.inference_mode()
+def process_text_gradio(text):
+    output = process_text(1, text, device)
+    return output["x_phones"][1::2], output["x"], output["x_lengths"]
+
+
+@torch.inference_mode()
+def synthesise_mel(text, text_length, n_timesteps, temperature, length_scale, spk):
+    spk = torch.tensor([spk], device=device, dtype=torch.long) if spk >= 0 else None
+    output = model.synthesise(
+        text,
+        text_length,
+        n_timesteps=n_timesteps,
+        temperature=temperature,
+        spks=spk,
+        length_scale=length_scale,
+    )
+    output["waveform"] = to_waveform(output["mel"], vocoder, denoiser)
+    with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as fp:
+        sf.write(fp.name, output["waveform"], 22050, "PCM_24")
+
+    return fp.name, plot_tensor(output["mel"].squeeze().cpu().numpy())
+
+
+def multispeaker_example_cacher(text, n_timesteps, mel_temp, length_scale, spk):
+    global CURRENTLY_LOADED_MODEL  # pylint: disable=global-statement
+    if CURRENTLY_LOADED_MODEL != "matcha_vctk":
+        global model, vocoder, denoiser  # pylint: disable=global-statement
+        model, vocoder, denoiser = load_model("matcha_vctk", "hifigan_univ_v1")
+        CURRENTLY_LOADED_MODEL = "matcha_vctk"
+
+    phones, text, text_lengths = process_text_gradio(text)
+    audio, mel_spectrogram = synthesise_mel(text, text_lengths, n_timesteps, mel_temp, length_scale, spk)
+    return phones, audio, mel_spectrogram
+
+
+def ljspeech_example_cacher(text, n_timesteps, mel_temp, length_scale, spk=-1):
+    global CURRENTLY_LOADED_MODEL  # pylint: disable=global-statement
+    if CURRENTLY_LOADED_MODEL != "akyl_ai":
+        global model, vocoder, denoiser  # pylint: disable=global-statement
+        model, vocoder, denoiser = load_model("akyl_ai", "hifigan_T2_v1")
+        CURRENTLY_LOADED_MODEL = "akyl_ai"
+
+    phones, text, text_lengths = process_text_gradio(text)
+    audio, mel_spectrogram = synthesise_mel(text, text_lengths, n_timesteps, mel_temp, length_scale, spk)
+    return phones, audio, mel_spectrogram
+
+
+def main():
+    description = """# 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
+    ### [Shivam Mehta](https://www.kth.se/profile/smehta), [Ruibo Tu](https://www.kth.se/profile/ruibo), [Jonas Beskow](https://www.kth.se/profile/beskow), [Éva Székely](https://www.kth.se/profile/szekely), and [Gustav Eje Henter](https://people.kth.se/~ghe/)
+    We propose 🍵 Matcha-TTS, a new approach to non-autoregressive neural TTS, that uses conditional flow matching (similar to rectified flows) to speed up ODE-based speech synthesis. Our method:
+
+
+    * Is probabilistic
+    * Has compact memory footprint
+    * Sounds highly natural
+    * Is very fast to synthesise from
+
+
+    Check out our [demo page](https://shivammehta25.github.io/Matcha-TTS). Read our [arXiv preprint for more details](https://arxiv.org/abs/2309.03199).
+    Code is available in our [GitHub repository](https://github.com/shivammehta25/Matcha-TTS), along with pre-trained models.
+
+    Cached examples are available at the bottom of the page.
+    """
+
+    with gr.Blocks(title="🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching") as demo:
+        processed_text = gr.State(value=None)
+        processed_text_len = gr.State(value=None)
+
+        with gr.Box():
+            with gr.Row():
+                gr.Markdown(description, scale=3)
+                with gr.Column():
+                    gr.Image(LOGO_URL, label="Matcha-TTS logo", height=50, width=50, scale=1, show_label=False)
+                    html = '<br><iframe width="560" height="315" src="https://www.youtube.com/embed/xmvJkz3bqw0?si=jN7ILyDsbPwJCGoa" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen></iframe>'
+                    gr.HTML(html)
+
+        with gr.Box():
+            radio_options = list(RADIO_OPTIONS.keys())
+            model_type = gr.Radio(
+                radio_options, value=radio_options[0], label="Choose a Model", interactive=True, container=False
+            )
+
+            with gr.Row():
+                gr.Markdown("# Text Input")
+            with gr.Row():
+                text = gr.Textbox(value="", lines=2, label="Text to synthesise", scale=3)
+                spk_slider = gr.Slider(
+                    minimum=0, maximum=107, step=1, value=args.spk, label="Speaker ID", interactive=True, scale=1
+                )
+
+            with gr.Row():
+                gr.Markdown("### Hyper parameters")
+            with gr.Row():
+                n_timesteps = gr.Slider(
+                    label="Number of ODE steps",
+                    minimum=1,
+                    maximum=100,
+                    step=1,
+                    value=10,
+                    interactive=True,
+                )
+                length_scale = gr.Slider(
+                    label="Length scale (Speaking rate)",
+                    minimum=0.5,
+                    maximum=1.5,
+                    step=0.05,
+                    value=1.0,
+                    interactive=True,
+                )
+                mel_temp = gr.Slider(
+                    label="Sampling temperature",
+                    minimum=0.00,
+                    maximum=2.001,
+                    step=0.16675,
+                    value=0.667,
+                    interactive=True,
+                )
+
+                synth_btn = gr.Button("Synthesise")
+
+        with gr.Box():
+            with gr.Row():
+                gr.Markdown("### Phonetised text")
+                phonetised_text = gr.Textbox(interactive=False, scale=10, label="Phonetised text")
+
+        with gr.Box():
+            with gr.Row():
+                mel_spectrogram = gr.Image(interactive=False, label="mel spectrogram")
+
+                # with gr.Row():
+                audio = gr.Audio(interactive=False, label="Audio")
+
+        with gr.Row(visible=False) as example_row_lj_speech:
+            examples = gr.Examples(  # pylint: disable=unused-variable
+                examples=[
+                    [
+                        "We propose Matcha-TTS, a new approach to non-autoregressive neural TTS, that uses conditional flow matching (similar to rectified flows) to speed up O D E-based speech synthesis.",
+                        50,
+                        0.677,
+                        0.95,
+                    ],
+                    [
+                        "The Secret Service believed that it was very doubtful that any President would ride regularly in a vehicle with a fixed top, even though transparent.",
+                        2,
+                        0.677,
+                        0.95,
+                    ],
+                    [
+                        "The Secret Service believed that it was very doubtful that any President would ride regularly in a vehicle with a fixed top, even though transparent.",
+                        4,
+                        0.677,
+                        0.95,
+                    ],
+                    [
+                        "The Secret Service believed that it was very doubtful that any President would ride regularly in a vehicle with a fixed top, even though transparent.",
+                        10,
+                        0.677,
+                        0.95,
+                    ],
+                  
+                ],
+                fn=ljspeech_example_cacher,
+                inputs=[text, n_timesteps, mel_temp, length_scale],
+                outputs=[phonetised_text, audio, mel_spectrogram],
+                cache_examples=True,
+            )
+
+        with gr.Row() as example_row_multispeaker:
+            multi_speaker_examples = gr.Examples(  # pylint: disable=unused-variable
+                examples=[
+                    [
+                        "Hello everyone! I am speaker 0 and I am here to tell you that Matcha-TTS is amazing!",
+                        10,
+                        0.677,
+                        0.85,
+                        0,
+                    ],
+                    [
+                        "Hello everyone! I am speaker 16 and I am here to tell you that Matcha-TTS is amazing!",
+                        10,
+                        0.677,
+                        0.85,
+                        16,
+                    ],
+                    [
+                ],
+                fn=multispeaker_example_cacher,
+                inputs=[text, n_timesteps, mel_temp, length_scale, spk_slider],
+                outputs=[phonetised_text, audio, mel_spectrogram],
+                cache_examples=True,
+                label="Multi Speaker Examples",
+            )
+
+        model_type.change(lambda x: gr.update(interactive=False), inputs=[synth_btn], outputs=[synth_btn]).then(
+            load_model_ui,
+            inputs=[model_type, text],
+            outputs=[text, synth_btn, spk_slider, example_row_lj_speech, example_row_multispeaker, length_scale],
+        )
+
+        synth_btn.click(
+            fn=process_text_gradio,
+            inputs=[
+                text,
+            ],
+            outputs=[phonetised_text, processed_text, processed_text_len],
+            api_name="matcha_tts",
+            queue=True,
+        ).then(
+            fn=synthesise_mel,
+            inputs=[processed_text, processed_text_len, n_timesteps, mel_temp, length_scale, spk_slider],
+            outputs=[audio, mel_spectrogram],
+        )
+
+        demo.queue().launch(share=True)
+
+
+if __name__ == "__main__":
+    main()

configs/__init__.py

@@ -0,0 +1 @@
+# this file is needed here to include configs when building project as a package

configs/callbacks/default.yaml

@@ -0,0 +1,5 @@
+defaults:
+  - model_checkpoint.yaml
+  - model_summary.yaml
+  - rich_progress_bar.yaml
+  - _self_

configs/callbacks/model_checkpoint.yaml

@@ -0,0 +1,17 @@
+# https://lightning.ai/docs/pytorch/stable/api/lightning.pytorch.callbacks.ModelCheckpoint.html
+
+model_checkpoint:
+  _target_: lightning.pytorch.callbacks.ModelCheckpoint
+  dirpath: ${paths.output_dir}/checkpoints # directory to save the model file
+  filename: checkpoint_{epoch:03d}  # checkpoint filename
+  monitor: epoch # name of the logged metric which determines when model is improving
+  verbose: False # verbosity mode
+  save_last: true # additionally always save an exact copy of the last checkpoint to a file last.ckpt
+  save_top_k: 5 # save k best models (determined by above metric)
+  mode: "max" # "max" means higher metric value is better, can be also "min"
+  auto_insert_metric_name: True # when True, the checkpoints filenames will contain the metric name
+  save_weights_only: False # if True, then only the model’s weights will be saved
+  every_n_train_steps: null # number of training steps between checkpoints
+  train_time_interval: null # checkpoints are monitored at the specified time interval
+  every_n_epochs: 10 # number of epochs between checkpoints
+  save_on_train_epoch_end: null # whether to run checkpointing at the end of the training epoch or the end of validation

configs/callbacks/model_summary.yaml

@@ -0,0 +1,5 @@
+# https://lightning.ai/docs/pytorch/stable/api/lightning.pytorch.callbacks.RichModelSummary.html
+
+model_summary:
+  _target_: lightning.pytorch.callbacks.RichModelSummary
+  max_depth: 3 # the maximum depth of layer nesting that the summary will include

configs/callbacks/rich_progress_bar.yaml

@@ -0,0 +1,4 @@
+# https://lightning.ai/docs/pytorch/latest/api/lightning.pytorch.callbacks.RichProgressBar.html
+
+rich_progress_bar:
+  _target_: lightning.pytorch.callbacks.RichProgressBar

configs/data/akylai.yaml

@@ -0,0 +1,21 @@
+_target_: matcha.data.text_mel_datamodule.TextMelDataModule
+name: akylai
+train_filelist_path: ./kany_dataset/kany_filelist_train.txt
+valid_filelist_path: ./kany_dataset/kany_filelist_test.txt
+batch_size: 32
+num_workers: 20
+pin_memory: True
+cleaners: [kyrgyz_cleaners]
+add_blank: True
+n_spks: 1
+n_fft: 1024
+n_feats: 80
+sample_rate: 22050
+hop_length: 256
+win_length: 1024
+f_min: 0
+f_max: 8000
+data_statistics:  # Computed for ljspeech dataset
+  mel_mean: -5.6814561
+  mel_std: 2.7337122
+seed: ${seed}

configs/data/hi-fi_en-US_female.yaml

@@ -0,0 +1,14 @@
+defaults:
+  - ljspeech
+  - _self_
+
+# Dataset URL: https://ast-astrec.nict.go.jp/en/release/hi-fi-captain/
+_target_: matcha.data.text_mel_datamodule.TextMelDataModule
+name: hi-fi_en-US_female
+train_filelist_path: data/filelists/hi-fi-captain-en-us-female_train.txt
+valid_filelist_path: data/filelists/hi-fi-captain-en-us-female_val.txt
+batch_size: 32
+cleaners: [english_cleaners_piper]
+data_statistics:  # Computed for this dataset
+  mel_mean: -6.38385
+  mel_std: 2.541796

configs/data/ljspeech.yaml

@@ -0,0 +1,22 @@
+_target_: matcha.data.text_mel_datamodule.TextMelDataModule
+name: ljspeech
+train_filelist_path: /content/kany_dataset/kany_filelist_train.txt
+valid_filelist_path: /content/kany_dataset/kany_filelist_test.txt
+batch_size: 16
+num_workers: 20
+pin_memory: True
+cleaners: [kyrgyz_cleaners]
+add_blank: True
+n_spks: 1
+n_fft: 1024
+n_feats: 80
+sample_rate: 22050
+hop_length: 256
+win_length: 1024
+f_min: 0
+f_max: 8000
+data_statistics:  # Computed for ljspeech dataset
+  mel_mean: -5.68145561
+  mel_std: 2.7337122
+seed: ${seed}
+

configs/data/vctk.yaml

@@ -0,0 +1,14 @@
+defaults:
+  - ljspeech
+  - _self_
+
+_target_: matcha.data.text_mel_datamodule.TextMelDataModule
+name: vctk
+train_filelist_path: data/filelists/vctk_audio_sid_text_train_filelist.txt
+valid_filelist_path: data/filelists/vctk_audio_sid_text_val_filelist.txt
+batch_size: 32
+add_blank: True
+n_spks: 109
+data_statistics:  # Computed for vctk dataset
+  mel_mean: -6.630575
+  mel_std: 2.482914

configs/debug/default.yaml

@@ -0,0 +1,35 @@
+# @package _global_
+
+# default debugging setup, runs 1 full epoch
+# other debugging configs can inherit from this one
+
+# overwrite task name so debugging logs are stored in separate folder
+task_name: "debug"
+
+# disable callbacks and loggers during debugging
+# callbacks: null
+# logger: null
+
+extras:
+  ignore_warnings: False
+  enforce_tags: False
+
+# sets level of all command line loggers to 'DEBUG'
+# https://hydra.cc/docs/tutorials/basic/running_your_app/logging/
+hydra:
+  job_logging:
+    root:
+      level: DEBUG
+
+  # use this to also set hydra loggers to 'DEBUG'
+  # verbose: True
+
+trainer:
+  max_epochs: 1
+  accelerator: cpu # debuggers don't like gpus
+  devices: 1 # debuggers don't like multiprocessing
+  detect_anomaly: true # raise exception if NaN or +/-inf is detected in any tensor
+
+data:
+  num_workers: 0 # debuggers don't like multiprocessing
+  pin_memory: False # disable gpu memory pin

configs/debug/fdr.yaml

@@ -0,0 +1,9 @@
+# @package _global_
+
+# runs 1 train, 1 validation and 1 test step
+
+defaults:
+  - default
+
+trainer:
+  fast_dev_run: true

configs/debug/limit.yaml

@@ -0,0 +1,12 @@
+# @package _global_
+
+# uses only 1% of the training data and 5% of validation/test data
+
+defaults:
+  - default
+
+trainer:
+  max_epochs: 3
+  limit_train_batches: 0.01
+  limit_val_batches: 0.05
+  limit_test_batches: 0.05

configs/debug/overfit.yaml

@@ -0,0 +1,13 @@
+# @package _global_
+
+# overfits to 3 batches
+
+defaults:
+  - default
+
+trainer:
+  max_epochs: 20
+  overfit_batches: 3
+
+# model ckpt and early stopping need to be disabled during overfitting
+callbacks: null

configs/debug/profiler.yaml

@@ -0,0 +1,15 @@
+# @package _global_
+
+# runs with execution time profiling
+
+defaults:
+  - default
+
+trainer:
+  max_epochs: 1
+  # profiler: "simple"
+  profiler: "advanced"
+  # profiler: "pytorch"
+  accelerator: gpu
+
+  limit_train_batches: 0.02

configs/eval.yaml

@@ -0,0 +1,18 @@
+# @package _global_
+
+defaults:
+  - _self_
+  - data: akylai # choose datamodule with `test_dataloader()` for evaluation
+  - model: matcha
+  - logger: null
+  - trainer: default
+  - paths: default
+  - extras: default
+  - hydra: default
+
+task_name: "eval"
+
+tags: ["dev"]
+
+# passing checkpoint path is necessary for evaluation
+ckpt_path: ???

configs/experiment/akylai.yaml

@@ -0,0 +1,14 @@
+# @package _global_
+
+# to execute this experiment run:
+# python train.py experiment=multispeaker
+
+defaults:
+  - override /data: akylai.yaml
+
+# all parameters below will be merged with parameters from default configurations set above
+# this allows you to overwrite only specified parameters
+
+tags: ["akylai"]
+
+run_name: akylai

configs/experiment/hifi_dataset_piper_phonemizer.yaml

@@ -0,0 +1,14 @@
+# @package _global_
+
+# to execute this experiment run:
+# python train.py experiment=multispeaker
+
+defaults:
+  - override /data: hi-fi_en-US_female.yaml
+
+# all parameters below will be merged with parameters from default configurations set above
+# this allows you to overwrite only specified parameters
+
+tags: ["hi-fi", "single_speaker", "piper_phonemizer", "en_US", "female"]
+
+run_name: hi-fi_en-US_female_piper_phonemizer

configs/experiment/ljspeech.yaml

@@ -0,0 +1,14 @@
+# @package _global_
+
+# to execute this experiment run:
+# python train.py experiment=multispeaker
+
+defaults:
+  - override /data: ljspeech.yaml
+
+# all parameters below will be merged with parameters from default configurations set above
+# this allows you to overwrite only specified parameters
+
+tags: ["ljspeech"]
+
+run_name: ljspeech

configs/experiment/ljspeech_min_memory.yaml

@@ -0,0 +1,18 @@
+# @package _global_
+
+# to execute this experiment run:
+# python train.py experiment=multispeaker
+
+defaults:
+  - override /data: ljspeech.yaml
+
+# all parameters below will be merged with parameters from default configurations set above
+# this allows you to overwrite only specified parameters
+
+tags: ["ljspeech"]
+
+run_name: ljspeech_min
+
+
+model:
+  out_size: 172

configs/experiment/multispeaker.yaml

@@ -0,0 +1,14 @@
+# @package _global_
+
+# to execute this experiment run:
+# python train.py experiment=multispeaker
+
+defaults:
+  - override /data: vctk.yaml
+
+# all parameters below will be merged with parameters from default configurations set above
+# this allows you to overwrite only specified parameters
+
+tags: ["multispeaker"]
+
+run_name: multispeaker

configs/extras/default.yaml

@@ -0,0 +1,8 @@
+# disable python warnings if they annoy you
+ignore_warnings: False
+
+# ask user for tags if none are provided in the config
+enforce_tags: True
+
+# pretty print config tree at the start of the run using Rich library
+print_config: True

configs/hparams_search/mnist_optuna.yaml

@@ -0,0 +1,52 @@
+# @package _global_
+
+# example hyperparameter optimization of some experiment with Optuna:
+# python train.py -m hparams_search=mnist_optuna experiment=example
+
+defaults:
+  - override /hydra/sweeper: optuna
+
+# choose metric which will be optimized by Optuna
+# make sure this is the correct name of some metric logged in lightning module!
+optimized_metric: "val/acc_best"
+
+# here we define Optuna hyperparameter search
+# it optimizes for value returned from function with @hydra.main decorator
+# docs: https://hydra.cc/docs/next/plugins/optuna_sweeper
+hydra:
+  mode: "MULTIRUN" # set hydra to multirun by default if this config is attached
+
+  sweeper:
+    _target_: hydra_plugins.hydra_optuna_sweeper.optuna_sweeper.OptunaSweeper
+
+    # storage URL to persist optimization results
+    # for example, you can use SQLite if you set 'sqlite:///example.db'
+    storage: null
+
+    # name of the study to persist optimization results
+    study_name: null
+
+    # number of parallel workers
+    n_jobs: 1
+
+    # 'minimize' or 'maximize' the objective
+    direction: maximize
+
+    # total number of runs that will be executed
+    n_trials: 20
+
+    # choose Optuna hyperparameter sampler
+    # you can choose bayesian sampler (tpe), random search (without optimization), grid sampler, and others
+    # docs: https://optuna.readthedocs.io/en/stable/reference/samplers.html
+    sampler:
+      _target_: optuna.samplers.TPESampler
+      seed: 1234
+      n_startup_trials: 10 # number of random sampling runs before optimization starts
+
+    # define hyperparameter search space
+    params:
+      model.optimizer.lr: interval(0.0001, 0.1)
+      data.batch_size: choice(32, 64, 128, 256)
+      model.net.lin1_size: choice(64, 128, 256)
+      model.net.lin2_size: choice(64, 128, 256)
+      model.net.lin3_size: choice(32, 64, 128, 256)

configs/hydra/default.yaml

@@ -0,0 +1,19 @@
+# https://hydra.cc/docs/configure_hydra/intro/
+
+# enable color logging
+defaults:
+  - override hydra_logging: colorlog
+  - override job_logging: colorlog
+
+# output directory, generated dynamically on each run
+run:
+  dir: ${paths.log_dir}/${task_name}/${run_name}/runs/${now:%Y-%m-%d}_${now:%H-%M-%S}
+sweep:
+  dir: ${paths.log_dir}/${task_name}/${run_name}/multiruns/${now:%Y-%m-%d}_${now:%H-%M-%S}
+  subdir: ${hydra.job.num}
+
+job_logging:
+  handlers:
+    file:
+      # Incorporates fix from https://github.com/facebookresearch/hydra/pull/2242
+      filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log

configs/logger/aim.yaml

@@ -0,0 +1,28 @@
+# https://aimstack.io/
+
+# example usage in lightning module:
+# https://github.com/aimhubio/aim/blob/main/examples/pytorch_lightning_track.py
+
+# open the Aim UI with the following command (run in the folder containing the `.aim` folder):
+# `aim up`
+
+aim:
+  _target_: aim.pytorch_lightning.AimLogger
+  repo: ${paths.root_dir} # .aim folder will be created here
+  # repo: "aim://ip_address:port" # can instead provide IP address pointing to Aim remote tracking server which manages the repo, see https://aimstack.readthedocs.io/en/latest/using/remote_tracking.html#
+
+  # aim allows to group runs under experiment name
+  experiment: null # any string, set to "default" if not specified
+
+  train_metric_prefix: "train/"
+  val_metric_prefix: "val/"
+  test_metric_prefix: "test/"
+
+  # sets the tracking interval in seconds for system usage metrics (CPU, GPU, memory, etc.)
+  system_tracking_interval: 10 # set to null to disable system metrics tracking
+
+  # enable/disable logging of system params such as installed packages, git info, env vars, etc.
+  log_system_params: true
+
+  # enable/disable tracking console logs (default value is true)
+  capture_terminal_logs: false # set to false to avoid infinite console log loop issue https://github.com/aimhubio/aim/issues/2550

configs/logger/comet.yaml

@@ -0,0 +1,12 @@
+# https://www.comet.ml
+
+comet:
+  _target_: lightning.pytorch.loggers.comet.CometLogger
+  api_key: ${oc.env:COMET_API_TOKEN} # api key is loaded from environment variable
+  save_dir: "${paths.output_dir}"
+  project_name: "lightning-hydra-template"
+  rest_api_key: null
+  # experiment_name: ""
+  experiment_key: null # set to resume experiment
+  offline: False
+  prefix: ""

configs/logger/csv.yaml

@@ -0,0 +1,7 @@
+# csv logger built in lightning
+
+csv:
+  _target_: lightning.pytorch.loggers.csv_logs.CSVLogger
+  save_dir: "${paths.output_dir}"
+  name: "csv/"
+  prefix: ""

configs/logger/many_loggers.yaml

@@ -0,0 +1,9 @@
+# train with many loggers at once
+
+defaults:
+  # - comet
+  - csv
+  # - mlflow
+  # - neptune
+  - tensorboard
+  - wandb

configs/logger/mlflow.yaml

@@ -0,0 +1,12 @@
+# https://mlflow.org
+
+mlflow:
+  _target_: lightning.pytorch.loggers.mlflow.MLFlowLogger
+  # experiment_name: ""
+  # run_name: ""
+  tracking_uri: ${paths.log_dir}/mlflow/mlruns # run `mlflow ui` command inside the `logs/mlflow/` dir to open the UI
+  tags: null
+  # save_dir: "./mlruns"
+  prefix: ""
+  artifact_location: null
+  # run_id: ""

configs/logger/neptune.yaml

@@ -0,0 +1,9 @@
+# https://neptune.ai
+
+neptune:
+  _target_: lightning.pytorch.loggers.neptune.NeptuneLogger
+  api_key: ${oc.env:NEPTUNE_API_TOKEN} # api key is loaded from environment variable
+  project: username/lightning-hydra-template
+  # name: ""
+  log_model_checkpoints: True
+  prefix: ""

configs/logger/tensorboard.yaml

@@ -0,0 +1,10 @@
+# https://www.tensorflow.org/tensorboard/
+
+tensorboard:
+  _target_: lightning.pytorch.loggers.tensorboard.TensorBoardLogger
+  save_dir: "${paths.output_dir}/tensorboard/"
+  name: null
+  log_graph: False
+  default_hp_metric: True
+  prefix: ""
+  # version: ""

configs/logger/wandb.yaml

@@ -0,0 +1,16 @@
+# https://wandb.ai
+
+wandb:
+  _target_: lightning.pytorch.loggers.wandb.WandbLogger
+  # name: "" # name of the run (normally generated by wandb)
+  save_dir: "${paths.output_dir}"
+  offline: False
+  id: null # pass correct id to resume experiment!
+  anonymous: null # enable anonymous logging
+  project: "lightning-hydra-template"
+  log_model: False # upload lightning ckpts
+  prefix: "" # a string to put at the beginning of metric keys
+  # entity: "" # set to name of your wandb team
+  group: ""
+  tags: []
+  job_type: ""

configs/model/cfm/default.yaml

@@ -0,0 +1,3 @@
+name: CFM
+solver: euler
+sigma_min: 1e-4

configs/model/decoder/default.yaml

@@ -0,0 +1,7 @@
+channels: [256, 256]
+dropout: 0.05
+attention_head_dim: 64
+n_blocks: 1
+num_mid_blocks: 2
+num_heads: 2
+act_fn: snakebeta

configs/model/encoder/default.yaml

@@ -0,0 +1,18 @@
+encoder_type: RoPE Encoder
+encoder_params:
+  n_feats: ${model.n_feats}
+  n_channels: 192
+  filter_channels: 768
+  filter_channels_dp: 256
+  n_heads: 2
+  n_layers: 6
+  kernel_size: 3
+  p_dropout: 0.1
+  spk_emb_dim: 64
+  n_spks: 1
+  prenet: true
+
+duration_predictor_params:
+  filter_channels_dp: ${model.encoder.encoder_params.filter_channels_dp}
+  kernel_size: 3
+  p_dropout: ${model.encoder.encoder_params.p_dropout}

configs/model/matcha.yaml

@@ -0,0 +1,15 @@
+defaults:
+  - _self_
+  - encoder: default.yaml
+  - decoder: default.yaml
+  - cfm: default.yaml
+  - optimizer: adam.yaml
+
+_target_: matcha.models.matcha_tts.MatchaTTS
+n_vocab: 178
+n_spks: ${data.n_spks}
+spk_emb_dim: 64
+n_feats: 80
+data_statistics: ${data.data_statistics}
+out_size: null # Must be divisible by 4
+prior_loss: true