Merge pull request #255 from idiap/drop-py39

Drop Python 3.9 support

.github/actions/setup-uv/action.yml

@@ -4,8 +4,9 @@ runs:
   using: 'composite'
   steps:
     - name: Install uv
-      uses: astral-sh/setup-uv@v4
+      uses: astral-sh/setup-uv@v5
       with:
-        version: "0.5.4"
+        version: "0.5.17"
         enable-cache: true
         cache-dependency-glob: "**/pyproject.toml"
+        python-version: ${{ matrix.python-version }}

.github/workflows/style_check.yml

@@ -9,15 +9,9 @@ on:
 jobs:
   lint:
     runs-on: ubuntu-latest
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: [3.9]
     steps:
       - uses: actions/checkout@v4
       - name: Setup uv
         uses: ./.github/actions/setup-uv
-      - name: Set up Python ${{ matrix.python-version }}
-        run: uv python install ${{ matrix.python-version }}
       - name: Lint check
         run: make lint

.github/workflows/tests.yml

@@ -22,14 +22,12 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: [3.9, "3.10", "3.11", "3.12"]
+        python-version: ["3.10", "3.11", "3.12"]
         subset: ["data_tests", "inference_tests", "test_aux", "test_text"]
     steps:
       - uses: actions/checkout@v4
       - name: Setup uv
         uses: ./.github/actions/setup-uv
-      - name: Set up Python ${{ matrix.python-version }}
-        run: uv python install ${{ matrix.python-version }}
       - name: Install Espeak
         if: contains(fromJSON('["inference_tests", "test_text"]'), matrix.subset)
         run: |
@@ -50,7 +48,7 @@ jobs:
       - name: Unit tests
         run: |
           resolution=highest
-          if [ "${{ matrix.python-version }}" == "3.9" ]; then
+          if [ "${{ matrix.python-version }}" == "3.10" ]; then
             resolution=lowest-direct
           fi
           uv run --resolution=$resolution --extra server --extra languages make ${{ matrix.subset }}
@@ -66,14 +64,12 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.9", "3.12"]
+        python-version: ["3.10", "3.12"]
         subset: ["test_tts", "test_tts2", "test_vocoder", "test_xtts"]
     steps:
       - uses: actions/checkout@v4
       - name: Setup uv
         uses: ./.github/actions/setup-uv
-      - name: Set up Python ${{ matrix.python-version }}
-        run: uv python install ${{ matrix.python-version }}
       - name: Install Espeak
         if: contains(fromJSON('["test_tts", "test_tts2", "test_xtts"]'), matrix.subset)
         run: |
@@ -94,7 +90,7 @@ jobs:
       - name: Integration tests
         run: |
           resolution=highest
-          if [ "${{ matrix.python-version }}" == "3.9" ]; then
+          if [ "${{ matrix.python-version }}" == "3.10" ]; then
             resolution=lowest-direct
           fi
           uv run --resolution=$resolution --extra server --extra languages make ${{ matrix.subset }}
@@ -116,8 +112,6 @@ jobs:
       - uses: actions/checkout@v4
       - name: Setup uv
         uses: ./.github/actions/setup-uv
-      - name: Set up Python ${{ matrix.python-version }}
-        run: uv python install ${{ matrix.python-version }}
       - name: Install Espeak
         run: |
           sudo apt-get update

.pre-commit-config.yaml

@@ -7,13 +7,9 @@ repos:
       - id: check-yaml
       - id: end-of-file-fixer
       - id: trailing-whitespace
-  - repo: "https://github.com/psf/black"
-    rev: 24.2.0
-    hooks:
-      - id: black
-        language_version: python3
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.7.0
+    rev: v0.9.1
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]
+      - id: ruff-format

CONTRIBUTING.md

@@ -88,7 +88,7 @@ curl -LsSf https://astral.sh/uv/install.sh | sh
     uv run make test_all  # run all the tests, report all the errors
     ```
 
-9. Format your code. We use ```black``` for code formatting.
+9. Format your code. We use ```ruff``` for code formatting.
 
     ```bash
     make style

Makefile

@@ -43,11 +43,11 @@ test_failed:  ## only run tests failed the last time.
 	coverage run -m pytest -x -v --last-failed tests
 
 style:	## update code style.
-	uv run --only-dev black ${target_dirs}
+	uv run --only-dev ruff format ${target_dirs}
 
 lint:	## run linters.
 	uv run --only-dev ruff check ${target_dirs}
-	uv run --only-dev black ${target_dirs} --check
+	uv run --only-dev ruff format ${target_dirs} --check
 
 system-deps:	## install linux system deps
 	sudo apt-get install -y libsndfile1-dev

README.md

@@ -116,7 +116,7 @@ You can also help us implement more models.
 <!-- start installation -->
 ## Installation
 
-🐸TTS is tested on Ubuntu 24.04 with **python >= 3.9, < 3.13**, but should also
+🐸TTS is tested on Ubuntu 24.04 with **python >= 3.10, < 3.13**, but should also
 work on Mac and Windows.
 
 If you are only interested in [synthesizing speech](https://coqui-tts.readthedocs.io/en/latest/inference.html) with the pretrained 🐸TTS models, installing from PyPI is the easiest option.

TTS/api.py

@@ -4,7 +4,6 @@
 import tempfile
 import warnings
 from pathlib import Path
-from typing import Optional, Union
 
 from torch import nn
 
@@ -22,15 +21,15 @@ def __init__(
         self,
         model_name: str = "",
         *,
-        model_path: Optional[str] = None,
-        config_path: Optional[str] = None,
-        vocoder_name: Optional[str] = None,
-        vocoder_path: Optional[str] = None,
-        vocoder_config_path: Optional[str] = None,
-        encoder_path: Optional[str] = None,
-        encoder_config_path: Optional[str] = None,
-        speakers_file_path: Optional[str] = None,
-        language_ids_file_path: Optional[str] = None,
+        model_path: str | None = None,
+        config_path: str | None = None,
+        vocoder_name: str | None = None,
+        vocoder_path: str | None = None,
+        vocoder_config_path: str | None = None,
+        encoder_path: str | None = None,
+        encoder_config_path: str | None = None,
+        speakers_file_path: str | None = None,
+        language_ids_file_path: str | None = None,
         progress_bar: bool = True,
         gpu: bool = False,
     ) -> None:
@@ -77,8 +76,8 @@ def __init__(
         super().__init__()
         self.manager = ModelManager(models_file=self.get_models_file_path(), progress_bar=progress_bar)
         self.config = load_config(config_path) if config_path else None
-        self.synthesizer: Optional[Synthesizer] = None
-        self.voice_converter: Optional[Synthesizer] = None
+        self.synthesizer: Synthesizer | None = None
+        self.voice_converter: Synthesizer | None = None
         self.model_name = ""
 
         self.vocoder_path = vocoder_path
@@ -156,8 +155,8 @@ def list_models() -> list[str]:
         return ModelManager(models_file=TTS.get_models_file_path(), progress_bar=False).list_models()
 
     def download_model_by_name(
-        self, model_name: str, vocoder_name: Optional[str] = None
-    ) -> tuple[Optional[Path], Optional[Path], Optional[Path], Optional[Path], Optional[Path]]:
+        self, model_name: str, vocoder_name: str | None = None
+    ) -> tuple[Path | None, Path | None, Path | None, Path | None, Path | None]:
         model_path, config_path, model_item = self.manager.download_model(model_name)
         if "fairseq" in model_name or (model_item is not None and isinstance(model_item["model_url"], list)):
             # return model directory if there are multiple files
@@ -176,7 +175,7 @@ def download_model_by_name(
             vocoder_path, vocoder_config_path, _ = self.manager.download_model(vocoder_name)
         return model_path, config_path, vocoder_path, vocoder_config_path, None
 
-    def load_model_by_name(self, model_name: str, vocoder_name: Optional[str] = None, *, gpu: bool = False) -> None:
+    def load_model_by_name(self, model_name: str, vocoder_name: str | None = None, *, gpu: bool = False) -> None:
         """Load one of the 🐸TTS models by name.
 
         Args:
@@ -185,7 +184,7 @@ def load_model_by_name(self, model_name: str, vocoder_name: Optional[str] = None
         """
         self.load_tts_model_by_name(model_name, vocoder_name, gpu=gpu)
 
-    def load_vc_model_by_name(self, model_name: str, vocoder_name: Optional[str] = None, *, gpu: bool = False) -> None:
+    def load_vc_model_by_name(self, model_name: str, vocoder_name: str | None = None, *, gpu: bool = False) -> None:
         """Load one of the voice conversion models by name.
 
         Args:
@@ -205,7 +204,7 @@ def load_vc_model_by_name(self, model_name: str, vocoder_name: Optional[str] = N
             use_cuda=gpu,
         )
 
-    def load_tts_model_by_name(self, model_name: str, vocoder_name: Optional[str] = None, *, gpu: bool = False) -> None:
+    def load_tts_model_by_name(self, model_name: str, vocoder_name: str | None = None, *, gpu: bool = False) -> None:
         """Load one of 🐸TTS models by name.
 
         Args:
@@ -261,11 +260,11 @@ def load_tts_model_by_path(self, model_path: str, config_path: str, *, gpu: bool
 
     def _check_arguments(
         self,
-        speaker: Optional[str] = None,
-        language: Optional[str] = None,
-        speaker_wav: Optional[str] = None,
-        emotion: Optional[str] = None,
-        speed: Optional[float] = None,
+        speaker: str | None = None,
+        language: str | None = None,
+        speaker_wav: str | None = None,
+        emotion: str | None = None,
+        speed: float | None = None,
         **kwargs,
     ) -> None:
         """Check if the arguments are valid for the model."""
@@ -284,11 +283,11 @@ def _check_arguments(
     def tts(
         self,
         text: str,
-        speaker: Optional[str] = None,
-        language: Optional[str] = None,
-        speaker_wav: Optional[str] = None,
-        emotion: Optional[str] = None,
-        speed: Optional[float] = None,
+        speaker: str | None = None,
+        language: str | None = None,
+        speaker_wav: str | None = None,
+        emotion: str | None = None,
+        speed: float | None = None,
         split_sentences: bool = True,
         **kwargs,
     ):
@@ -333,10 +332,10 @@ def tts(
     def tts_to_file(
         self,
         text: str,
-        speaker: Optional[str] = None,
-        language: Optional[str] = None,
-        speaker_wav: Optional[str] = None,
-        emotion: Optional[str] = None,
+        speaker: str | None = None,
+        language: str | None = None,
+        speaker_wav: str | None = None,
+        emotion: str | None = None,
         speed: float = 1.0,
         pipe_out=None,
         file_path: str = "output.wav",
@@ -388,7 +387,7 @@ def tts_to_file(
     def voice_conversion(
         self,
         source_wav: str,
-        target_wav: Union[str, list[str]],
+        target_wav: str | list[str],
     ):
         """Voice conversion with FreeVC. Convert source wav to target speaker.
 
@@ -406,7 +405,7 @@ def voice_conversion(
     def voice_conversion_to_file(
         self,
         source_wav: str,
-        target_wav: Union[str, list[str]],
+        target_wav: str | list[str],
         file_path: str = "output.wav",
         pipe_out=None,
     ) -> str:
@@ -430,9 +429,9 @@ def tts_with_vc(
         self,
         text: str,
         *,
-        language: Optional[str] = None,
-        speaker_wav: Union[str, list[str]],
-        speaker: Optional[str] = None,
+        language: str | None = None,
+        speaker_wav: str | list[str],
+        speaker: str | None = None,
         split_sentences: bool = True,
     ):
         """Convert text to speech with voice conversion.
@@ -473,10 +472,10 @@ def tts_with_vc_to_file(
         self,
         text: str,
         *,
-        language: Optional[str] = None,
-        speaker_wav: Union[str, list[str]],
+        language: str | None = None,
+        speaker_wav: str | list[str],
         file_path: str = "output.wav",
-        speaker: Optional[str] = None,
+        speaker: str | None = None,
         split_sentences: bool = True,
         pipe_out=None,
     ) -> str:

TTS/bin/compute_embeddings.py

@@ -3,7 +3,6 @@
 import os
 import sys
 from argparse import RawTextHelpFormatter
-from typing import Optional
 
 import torch
 from tqdm import tqdm
@@ -16,7 +15,7 @@
 from TTS.utils.generic_utils import ConsoleFormatter, setup_logger
 
 
-def parse_args(arg_list: Optional[list[str]]) -> argparse.Namespace:
+def parse_args(arg_list: list[str] | None) -> argparse.Namespace:
     parser = argparse.ArgumentParser(
         description="""Compute embedding vectors for each audio file in a dataset and store them keyed by `{dataset_name}#{file_path}` in a .pth file\n\n"""
         """
@@ -185,7 +184,7 @@ def compute_embeddings(
         print("Speaker embeddings saved at:", mapping_file_path)
 
 
-def main(arg_list: Optional[list[str]] = None):
+def main(arg_list: list[str] | None = None):
     setup_logger("TTS", level=logging.INFO, stream=sys.stdout, formatter=ConsoleFormatter())
     args = parse_args(arg_list)
 

TTS/bin/compute_statistics.py

@@ -1,12 +1,10 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 
 import argparse
 import glob
 import logging
 import os
 import sys
-from typing import Optional
 
 import numpy as np
 from tqdm import tqdm
@@ -18,7 +16,7 @@
 from TTS.utils.generic_utils import ConsoleFormatter, setup_logger
 
 
-def parse_args(arg_list: Optional[list[str]]) -> tuple[argparse.Namespace, list[str]]:
+def parse_args(arg_list: list[str] | None) -> tuple[argparse.Namespace, list[str]]:
     parser = argparse.ArgumentParser(description="Compute mean and variance of spectrogtram features.")
     parser.add_argument("config_path", type=str, help="TTS config file path to define audio processin parameters.")
     parser.add_argument("out_path", type=str, help="save path (directory and filename).")
@@ -31,7 +29,7 @@ def parse_args(arg_list: Optional[list[str]]) -> tuple[argparse.Namespace, list[
     return parser.parse_known_args(arg_list)
 
 
-def main(arg_list: Optional[list[str]] = None):
+def main(arg_list: list[str] | None = None):
     """Run preprocessing process."""
     setup_logger("TTS", level=logging.INFO, stream=sys.stderr, formatter=ConsoleFormatter())
     args, overrides = parse_args(arg_list)

TTS/bin/extract_tts_spectrograms.py

@@ -5,7 +5,6 @@
 import logging
 import sys
 from pathlib import Path
-from typing import Optional
 
 import numpy as np
 import torch
@@ -27,7 +26,7 @@
 use_cuda = torch.cuda.is_available()
 
 
-def parse_args(arg_list: Optional[list[str]]) -> argparse.Namespace:
+def parse_args(arg_list: list[str] | None) -> argparse.Namespace:
     parser = argparse.ArgumentParser()
     parser.add_argument("--config_path", type=str, help="Path to config file for training.", required=True)
     parser.add_argument("--checkpoint_path", type=str, help="Model file to be restored.", required=True)
@@ -244,7 +243,7 @@ def extract_spectrograms(
             f.write(f"{data[0] / data[1]}.npy\n")
 
 
-def main(arg_list: Optional[list[str]] = None) -> None:
+def main(arg_list: list[str] | None = None) -> None:
     setup_logger("TTS", level=logging.INFO, stream=sys.stdout, formatter=ConsoleFormatter())
     args = parse_args(arg_list)
     config = load_config(args.config_path)