v0.24.0

.dockerignore

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

.github/ISSUE_TEMPLATE/bug_report.yaml

@@ -59,7 +59,7 @@ body:
         You can either run `TTS/bin/collect_env_info.py`
 
         ```bash
-        wget https://raw.githubusercontent.com/coqui-ai/TTS/main/TTS/bin/collect_env_info.py
+        wget https://raw.githubusercontent.com/idiap/coqui-ai-TTS/main/TTS/bin/collect_env_info.py
         python collect_env_info.py
         ```
 

.github/ISSUE_TEMPLATE/config.yml

@@ -1,8 +1,8 @@
 blank_issues_enabled: false
 contact_links:
   - name: CoquiTTS GitHub Discussions
-    url: https://github.com/coqui-ai/TTS/discussions
+    url: https://github.com/idiap/coqui-ai-TTS/discussions
     about: Please ask and answer questions here.
   - name: Coqui Security issue disclosure
-    url: mailto:info@coqui.ai
+    url: mailto:enno.hermann@gmail.com
     about: Please report security vulnerabilities here.

.github/PR_TEMPLATE.md

@@ -5,11 +5,3 @@ Welcome to the 🐸TTS project! We are excited to see your interest, and appreci
 This repository is governed by the Contributor Covenant Code of Conduct. For more details, see the [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md) file.
 
 In order to make a good pull request, please see our [CONTRIBUTING.md](CONTRIBUTING.md) file.
-
-Before accepting your pull request, you will be asked to sign a [Contributor License Agreement](https://cla-assistant.io/coqui-ai/TTS).
-
-This [Contributor License Agreement](https://cla-assistant.io/coqui-ai/TTS):
-
-- Protects you, Coqui, and the users of the code.
-- Does not change your rights to use your contributions for any purpose.
-- Does not change the license of the 🐸TTS project. It just makes the terms of your contribution clearer and lets us know you are OK to contribute.

.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/encoder/utils/prepare_voxceleb.py

@@ -29,6 +29,8 @@
 
 import soundfile as sf
 
+from TTS.utils.generic_utils import ConsoleFormatter, setup_logger
+
 logger = logging.getLogger(__name__)
 
 SUBSETS = {
@@ -214,7 +216,7 @@ def processor(directory, subset, force_process):
 
 
 if __name__ == "__main__":
-    logging.getLogger("TTS").setLevel(logging.INFO)
+    setup_logger("TTS", level=logging.INFO, screen=True, formatter=ConsoleFormatter())
     if len(sys.argv) != 4:
         print("Usage: python prepare_data.py save_directory user password")
         sys.exit()