add submodule

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,38 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**To Reproduce**
+Steps to reproduce the behavior:
+1. Go to '...'
+2. Click on '....'
+3. Scroll down to '....'
+4. See error
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
+
+**Desktop (please complete the following information):**
+ - OS: [e.g. iOS]
+ - Browser [e.g. chrome, safari]
+ - Version [e.g. 22]
+
+**Smartphone (please complete the following information):**
+ - Device: [e.g. iPhone6]
+ - OS: [e.g. iOS8.1]
+ - Browser [e.g. stock browser, safari]
+ - Version [e.g. 22]
+
+**Additional context**
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,20 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+
+**Describe the solution you'd like**
+A clear and concise description of what you want to happen.
+
+**Describe alternatives you've considered**
+A clear and concise description of any alternative solutions or features you've considered.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.

.gitignore

@@ -3,160 +3,47 @@ __pycache__/
 *.py[cod]
 *$py.class
 
-# C extensions
+# Visual Studio Code files
-*.so
+.vscode
+.vs
 
-# Distribution / packaging
+# PyCharm files
-.Python
+.idea
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
 
-# PyInstaller
+# Eclipse Project settings
-#  Usually these files are written by a python script from a template
+*.*project
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+.settings
-*.manifest
-*.spec
 
-# Installer logs
+# Sublime Text settings
-pip-log.txt
+*.sublime-workspace
-pip-delete-this-directory.txt
+*.sublime-project
 
-# Unit test / coverage reports
+# Editor temporaries
-htmlcov/
+*.swn
-.tox/
+*.swo
-.nox/
+*.swp
-.coverage
+*.swm
-.coverage.*
+*~
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-cover/
 
-# Translations
+# IPython notebook checkpoints
-*.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
-.pybuilder/
-target/
-
-# Jupyter Notebook
 .ipynb_checkpoints
 
-# IPython
+# macOS dir files
-profile_default/
+.DS_Store
-ipython_config.py
 
-# pyenv
+exp
-#   For a library or package, you might want to ignore these files since the code is
+data
-#   intended to run in multiple environments; otherwise, check them in:
+raw_wav
-# .python-version
+tensorboard
+**/*build*
 
-# pipenv
+# Clangd files
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+.cache
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+compile_commands.json
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
 
-# poetry
+# train/inference files
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+*.wav
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
+*.pt
-#   commonly ignored for libraries.
+pretrained_models/*
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+*_pb2_grpc.py
-#poetry.lock
+*_pb2.py
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#pdm.lock
-#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
-#   in version control.
-#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
-.pdm.toml
-.pdm-python
-.pdm-build/
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.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/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/

.gitmodules

@@ -0,0 +1,6 @@
+[submodule "third_party/AcademiCodec"]
+	path = third_party/AcademiCodec
+	url = https://github.com/yangdongchao/AcademiCodec.git
+[submodule "third_party/Matcha-TTS"]
+	path = third_party/Matcha-TTS
+	url = https://github.com/shivammehta25/Matcha-TTS.git

cosyvoice/bin/train.py

@@ -75,8 +75,7 @@ def get_args():
     parser.add_argument('--timeout',
                         default=30,
                         type=int,
-                        help='timeout (in seconds) of cosyvoice_join. ' +
+                        help='timeout (in seconds) of cosyvoice_join.')
-                        '30s for aishell & 300s for wenetspeech')
     parser = deepspeed.add_config_arguments(parser)
     args = parser.parse_args()
     return args

cosyvoice/transformer/attention.py

@@ -152,7 +152,7 @@ class MultiHeadedAttention(nn.Module):
                 4.If the different position in decoder see different block
                 of the encoder, such as Mocha, the passed in mask could be
                 in (#batch, L, T) shape. But there is no such case in current
-                Wenet.
+                CosyVoice.
             cache (torch.Tensor): Cache tensor (1, head, cache_t, d_k * 2),
                 where `cache_t == chunk_size * num_decoding_left_chunks`
                 and `head * d_k == size`