Merge pull request #19 from idiap/toml

Move from setup.py to pyproject.toml, simplify requirements

.dockerignore

@@ -6,4 +6,4 @@ TTS.egg-info/
 tests/outputs/*
 tests/train_outputs/*
 __pycache__/
-*.pyc
+*.pyc

.github/stale.yml

@@ -15,4 +15,3 @@ markComment: >
   for your contributions. You might also look our discussion channels.
 # Comment to post when closing a stale issue. Set to `false` to disable
 closeComment: false
-

.github/workflows/docker.yaml

@@ -42,7 +42,7 @@ jobs:
             branch=${github_ref#*refs/heads/} # strip prefix to get branch name
             tags="${base}:${branch},${base}:${{ github.sha }},"
           elif [[ "${{ startsWith(github.ref, 'refs/tags/') }}" = "true" ]]; then
-            VERSION="v$(cat TTS/VERSION)"
+            VERSION="v$(grep -m 1 version pyproject.toml | grep -P '\d+\.\d+\.\d+' -o)"
             if [[ "${{ github.ref }}" != "refs/tags/${VERSION}" ]]; then
               echo "Pushed tag does not match VERSION file. Aborting push."
               exit 1
@@ -63,3 +63,58 @@ jobs:
           push: ${{ github.event_name == 'push' }}
           build-args: "BASE=${{ matrix.base }}"
           tags: ${{ steps.compute-tag.outputs.tags }}
+  docker-dev-build:
+    name: "Build the development Docker image"
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        arch: ["amd64"]
+        base:
+        - "nvidia/cuda:11.8.0-base-ubuntu22.04" # GPU enabled
+    steps:
+      - uses: actions/checkout@v4
+      - name: Log in to the Container registry
+        uses: docker/login-action@v1
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Compute Docker tags, check VERSION file matches tag
+        id: compute-tag
+        run: |
+          set -ex
+          base="ghcr.io/idiap/coqui-tts-dev"
+          tags="" # PR build
+
+          if [[ ${{ matrix.base }} = "python:3.10.8-slim" ]]; then
+            base="ghcr.io/idiap/coqui-tts-dev-cpu"
+          fi
+
+          if [[ "${{ startsWith(github.ref, 'refs/heads/') }}" = "true" ]]; then
+            # Push to branch
+            github_ref="${{ github.ref }}"
+            branch=${github_ref#*refs/heads/} # strip prefix to get branch name
+            tags="${base}:${branch},${base}:${{ github.sha }},"
+          elif [[ "${{ startsWith(github.ref, 'refs/tags/') }}" = "true" ]]; then
+            VERSION="v$(grep -m 1 version pyproject.toml | grep -P '\d+\.\d+\.\d+' -o)"
+            if [[ "${{ github.ref }}" != "refs/tags/${VERSION}" ]]; then
+              echo "Pushed tag does not match VERSION file. Aborting push."
+              exit 1
+            fi
+            tags="${base}:${VERSION},${base}:latest,${base}:${{ github.sha }}"
+          fi
+          echo "::set-output name=tags::${tags}"
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v1
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v1
+      - name: Build and push
+        uses: docker/build-push-action@v2
+        with:
+          context: .
+          file: dockerfiles/Dockerfile.dev
+          platforms: linux/${{ matrix.arch }}
+          push: false
+          build-args: "BASE=${{ matrix.base }}"
+          tags: ${{ steps.compute-tag.outputs.tags }}

.github/workflows/pypi-release.yml

@@ -14,7 +14,7 @@ jobs:
       - name: Verify tag matches version
         run: |
           set -ex
-          version=$(cat TTS/VERSION)
+          version=$(grep -m 1 version pyproject.toml | grep -P '\d+\.\d+\.\d+' -o)
           tag="${GITHUB_REF/refs\/tags\/}"
           if [[ "v$version" != "$tag" ]]; then
             exit 1
@@ -42,10 +42,9 @@ jobs:
       - uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-      - name: Install pip requirements
+      - name: Install build requirements
         run: |
-          python -m pip install -U pip setuptools wheel build
-          python -m pip install -r requirements.txt
+          python -m pip install -U pip setuptools wheel build numpy cython
       - name: Setup and install manylinux1_x86_64 wheel
         run: |
           python setup.py bdist_wheel --plat-name=manylinux1_x86_64

.github/workflows/tests.yml

@@ -45,7 +45,7 @@ jobs:
           sed -i 's/https:\/\/coqui.gateway.scarf.sh\//https:\/\/github.com\/coqui-ai\/TTS\/releases\/download\//g' TTS/.models.json
       - name: Install TTS
         run: |
-          python3 -m uv pip install --system "coqui-tts[dev,server,ja] @ ."
+          python3 -m uv pip install --system "coqui-tts[dev,server,languages] @ ."
           python3 setup.py egg_info
       - name: Unit tests
         run: make ${{ matrix.subset }}

.gitignore

@@ -169,4 +169,4 @@ wandb
 depot/*
 coqui_recipes/*
 local_scripts/*
-coqui_demos/*
+coqui_demos/*

.pre-commit-config.yaml

@@ -3,10 +3,8 @@ repos:
     rev: v4.5.0
     hooks:
       - id: check-yaml
-      # TODO: enable these later; there are plenty of violating
-      #       files that need to be fixed first
-      # - id: end-of-file-fixer
-      # - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
   - repo: "https://github.com/psf/black"
     rev: 24.2.0
     hooks:
@@ -17,3 +15,10 @@ repos:
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]
+  - repo: local
+    hooks:
+      - id: generate_requirements.py
+        name: generate_requirements.py
+        language: system
+        entry: python scripts/generate_requirements.py
+        files: "pyproject.toml|requirements.*\\.txt|tools/generate_requirements.py"

.readthedocs.yml

@@ -14,8 +14,9 @@ build:
 # Optionally set the version of Python and requirements required to build your docs
 python:
   install:
-    - requirements: docs/requirements.txt
-    - requirements: requirements.txt
+    - path: .
+      extra_requirements:
+        - docs
 
 # Build documentation in the docs/ directory with Sphinx
 sphinx:

CITATION.cff

@@ -17,4 +17,4 @@ keywords:
   - deep learning
   - artificial intelligence
   - text to speech
-  - TTS
+  - TTS

CODE_OF_CONDUCT.md

@@ -119,11 +119,11 @@ This Code of Conduct is adapted from the [Contributor Covenant][homepage],
 version 2.0, available at
 [https://www.contributor-covenant.org/version/2/0/code_of_conduct.html][v2.0].
 
-Community Impact Guidelines were inspired by 
+Community Impact Guidelines were inspired by
 [Mozilla's code of conduct enforcement ladder][Mozilla CoC].
 
 For answers to common questions about this code of conduct, see the FAQ at
-[https://www.contributor-covenant.org/faq][FAQ]. Translations are available 
+[https://www.contributor-covenant.org/faq][FAQ]. Translations are available
 at [https://www.contributor-covenant.org/translations][translations].
 
 [homepage]: https://www.contributor-covenant.org

CONTRIBUTING.md

@@ -60,7 +60,7 @@ The following steps are tested on an Ubuntu system.
 
     ```bash
     $ make system-deps  # intended to be used on Ubuntu (Debian). Let us know if you have a different OS.
-    $ make install
+    $ make install_dev
     ```
 
 4. Create a new branch with an informative name for your goal.

Dockerfile

@@ -3,6 +3,7 @@ FROM ${BASE}
 
 RUN apt-get update && apt-get upgrade -y
 RUN apt-get install -y --no-install-recommends gcc g++ make python3 python3-dev python3-pip python3-venv python3-wheel espeak-ng libsndfile1-dev && rm -rf /var/lib/apt/lists/*
+RUN pip3 install -U pip setuptools
 RUN pip3 install llvmlite --ignore-installed
 
 # Install Dependencies:

LICENSE.txt

@@ -35,7 +35,7 @@ Mozilla Public License Version 2.0
     means any form of the work other than Source Code Form.
 
 1.7. "Larger Work"
-    means a work that combines Covered Software with other material, in 
+    means a work that combines Covered Software with other material, in
     a separate file or files, that is not Covered Software.
 
 1.8. "License"

MANIFEST.in

@@ -1,15 +1,10 @@
 include README.md
 include LICENSE.txt
-include requirements.*.txt
 include *.cff
-include requirements.txt
-include TTS/VERSION
 recursive-include TTS *.json
 recursive-include TTS *.html
 recursive-include TTS *.png
 recursive-include TTS *.md
 recursive-include TTS *.py
 recursive-include TTS *.pyx
 recursive-include images *.png
-recursive-exclude tests *
-prune tests*

Makefile

@@ -1,5 +1,5 @@
 .DEFAULT_GOAL := help
-.PHONY: test system-deps dev-deps deps style lint install help docs
+.PHONY: test system-deps dev-deps style lint install install_dev help docs
 
 help:
 	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | sort | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}'
@@ -62,20 +62,15 @@ system-deps:	## install linux system deps
 dev-deps:  ## install development deps
 	pip install -r requirements.dev.txt
 
-doc-deps:  ## install docs dependencies
-	pip install -r docs/requirements.txt
-
 build-docs: ## build the docs
 	cd docs && make clean && make build
 
-hub-deps:  ## install deps for torch hub use
-	pip install -r requirements.hub.txt
-
-deps:	## install 🐸 requirements.
-	pip install -r requirements.txt
-
-install:	## install 🐸 TTS for development.
+install:	## install 🐸 TTS
 	pip install -e .[all]
 
+install_dev:	## install 🐸 TTS for development.
+	pip install -e .[all,dev]
+	pre-commit install
+
 docs:	## build the docs
 	$(MAKE) -C docs clean && $(MAKE) -C docs html

README.md

@@ -143,9 +143,35 @@ If you plan to code or train models, clone 🐸TTS and install it locally.
 
 ```bash
 git clone https://github.com/idiap/coqui-ai-TTS
-pip install -e .[all,dev,notebooks,server]  # Select the relevant extras
+pip install -e .
 ```
 
+### Optional dependencies
+
+The following extras allow the installation of optional dependencies:
+
+| Name | Description |
+|------|-------------|
+| `all` | All optional dependencies, except `dev` and `docs` |
+| `dev` | Development dependencies |
+| `dev` | Dependencies for building the documentation |
+| `notebooks` | Dependencies only used in notebooks |
+| `server` | Dependencies to run the TTS server |
+| `bn` | Bangla G2P |
+| `ja` | Japanese G2P |
+| `ko` | Korean G2P |
+| `zh` | Chinese G2P |
+| `languages` | All language-specific dependencies |
+
+You can install extras with one of the following commands:
+
+```bash
+pip install coqui-tts[server,ja]
+pip install -e .[server,ja]
+```
+
+### Platforms
+
 If you are on Ubuntu (Debian), you can also run following commands for installation.
 
 ```bash

TTS/__init__.py

@@ -1,6 +0,0 @@
-import os
-
-with open(os.path.join(os.path.dirname(__file__), "VERSION"), "r", encoding="utf-8") as f:
-    version = f.read().strip()
-
-__version__ = version

TTS/demos/xtts_ft_demo/requirements.txt

@@ -1,2 +1,2 @@
 faster_whisper==0.9.0
-gradio==4.7.1
+gradio==4.7.1

TTS/server/templates/details.html

@@ -128,4 +128,4 @@
 
 </body>
 
-</html>
+</html>

TTS/tts/layers/glow_tts/glow.py

@@ -1,5 +1,4 @@
 import torch
-from packaging.version import Version
 from torch import nn
 from torch.nn import functional as F
 
@@ -90,10 +89,7 @@ def __init__(self, channels, num_splits=4, no_jacobian=False, **kwargs):  # pyli
         self.no_jacobian = no_jacobian
         self.weight_inv = None
 
-        if Version(torch.__version__) < Version("1.9"):
-            w_init = torch.qr(torch.FloatTensor(self.num_splits, self.num_splits).normal_())[0]
-        else:
-            w_init = torch.linalg.qr(torch.FloatTensor(self.num_splits, self.num_splits).normal_(), "complete")[0]
+        w_init = torch.linalg.qr(torch.FloatTensor(self.num_splits, self.num_splits).normal_(), "complete")[0]
 
         if torch.det(w_init) < 0:
             w_init[:, 0] = -1 * w_init[:, 0]

TTS/tts/layers/xtts/perceiver_encoder.py

@@ -7,7 +7,6 @@
 import torch.nn.functional as F
 from einops import rearrange, repeat
 from einops.layers.torch import Rearrange
-from packaging import version
 from torch import einsum, nn
 
 
@@ -44,9 +43,6 @@ def __init__(self, dropout=0.0, causal=False, use_flash=False):
         self.register_buffer("mask", None, persistent=False)
 
         self.use_flash = use_flash
-        assert not (
-            use_flash and version.parse(torch.__version__) < version.parse("2.0.0")
-        ), "in order to use flash attention, you must be using pytorch 2.0 or above"
 
         # determine efficient attention configs for cuda and cpu
         self.config = namedtuple("EfficientAttentionConfig", ["enable_flash", "enable_math", "enable_mem_efficient"])

TTS/tts/layers/xtts/tokenizer.py

@@ -4,10 +4,7 @@
 import textwrap
 from functools import cached_property
 
-import pypinyin
 import torch
-from hangul_romanize import Transliter
-from hangul_romanize.rule import academic
 from num2words import num2words
 from spacy.lang.ar import Arabic
 from spacy.lang.en import English
@@ -577,6 +574,10 @@ def basic_cleaners(text):
 
 
 def chinese_transliterate(text):
+    try:
+        import pypinyin
+    except ImportError as e:
+        raise ImportError("Chinese requires: pypinyin") from e
     return "".join(
         [p[0] for p in pypinyin.pinyin(text, style=pypinyin.Style.TONE3, heteronym=False, neutral_tone_with_five=True)]
     )
@@ -589,6 +590,11 @@ def japanese_cleaners(text, katsu):
 
 
 def korean_transliterate(text):
+    try:
+        from hangul_romanize import Transliter
+        from hangul_romanize.rule import academic
+    except ImportError as e:
+        raise ImportError("Korean requires: hangul_romanize") from e
     r = Transliter(academic)
     return r.translit(text)