Move to package

CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## 3.2.0
+
+- Refactor as `piper_sample_generator` package
+
 ## 3.1.0
 
 - Support MPS acceleration on Apple Silicon

README.md

@@ -33,7 +33,7 @@ wget -O voices/en_US-lessac-medium.onnx.json 'https://huggingface.co/rhasspy/pip
 Generate a small set of samples with the CLI:
 
 ``` sh
-python3 generate_samples.py 'okay piper.' --model voices/en_US-lessac-medium.onnx --max-samples 10 --output-dir okay_piper/
+python3 -m piper_sample_generator 'okay piper.' --model voices/en_US-lessac-medium.onnx --max-samples 10 --output-dir okay_piper/
 ```
 
 Check the `okay_piper/` directory for 10 WAV files (named `0.wav` to `9.wav`).
@@ -53,7 +53,7 @@ wget -O models/en-us-libritts-high.pt 'https://github.com/rhasspy/piper-sample-g
 Generate a small set of samples with the CLI:
 
 ``` sh
-python3 generate_samples.py 'okay piper.' --model models/en-us-libritts-high.pt --max-samples 10 --output-dir okay_piper/
+python3 -m piper_sample_generator 'okay piper.' --model models/en-us-libritts-high.pt --max-samples 10 --output-dir okay_piper/
 ```
 
 Check the `okay_piper/` directory for 10 WAV files (named `0.wav` to `9.wav`).
@@ -61,7 +61,7 @@ Check the `okay_piper/` directory for 10 WAV files (named `0.wav` to `9.wav`).
 Generation can be much faster and more efficient if you have a GPU available and PyTorch is configured to use it. In this case, increase the batch size:
 
 ``` sh
-python3 generate_samples.py 'okay piper.' --model models/en-us-libritts-high.pt --max-samples 100 --batch-size 10 --output-dir okay_piper/
+python3 -m piper_sample_generator 'okay piper.' --model models/en-us-libritts-high.pt --max-samples 100 --batch-size 10 --output-dir okay_piper/
 ```
 
 On an NVidia 2080 Ti with 11GB, a batch size of 100 was possible (generating approximately 100 samples per second).
@@ -75,14 +75,14 @@ See `--help` for more options, including the `--length-scales` (speaking speeds)
 Once you have samples generated, you can augment them using [audiomentation](https://iver56.github.io/audiomentations/):
 
 ``` sh
-python3 augment.py --sample-rate 22050 okay_piper/ okay_piper_augmented/
+python3 -m piper_sample_generator.augment --sample-rate 22050 okay_piper/ okay_piper_augmented/
 ```
 
 This will do several things to each sample:
 
 1. Randomly decrease the volume
     * The original samples are normalized, so different volume levels are needed
-2. Randomly apply an [impulse response][] using the files in `impulses/`
+2. Randomly apply an [impulse response][] using the files in `piper_sample_generator/impulses/`
     * Change the acoustics of the sample to sound like the speaker was in a room with echo or using a poor quality microphone
 3. Resample to 16Khz for training (e.g., [openWakeWord][])
 

piper_sample_generator/__init__.py

@@ -0,0 +1 @@
+"""Piper sample generator."""

piper_sample_generator/__main__.py

@@ -16,6 +16,9 @@ import torch
 from piper import PiperVoice, SynthesisConfig
 from piper.phonemize_espeak import EspeakPhonemizer
 
+try:
+    from piper_train.vits import commons
+except ImportError:
     from piper_train.vits import commons
 
 _LOGGER = logging.getLogger(__name__)
@@ -176,7 +179,8 @@ def generate_samples(
             audio_numpy = audio.cpu().numpy()
 
             if torch.backends.mps.is_available():
-                # There seems to be a memory leak if we don't empty the cache after each batch with mps
+                # There seems to be a memory leak if we don't empty the cache
+                # after each batch with mps
                 torch.mps.empty_cache()
                 gc.collect()
 

piper_sample_generator/augment.py

@@ -1,12 +1,11 @@
 #!/usr/bin/env python3
 import argparse
 import audioop
-import sys
 import wave
 from pathlib import Path
 
 import numpy as np
-from audiomentations import Compose, ApplyImpulseResponse, Gain
+from audiomentations import ApplyImpulseResponse, Compose, Gain
 
 _DIR = Path(__file__).parent
 
@@ -35,9 +34,10 @@ def main() -> None:
         output_wav = output_dir / (input_wav.relative_to(input_dir))
         output_wav.parent.mkdir(parents=True, exist_ok=True)
 
-        with wave.open(str(input_wav), "rb") as input_wav_file, wave.open(
-            str(output_wav), "wb"
-        ) as output_wav_file:
+        with (
+            wave.open(str(input_wav), "rb") as input_wav_file,
+            wave.open(str(output_wav), "wb") as output_wav_file,
+        ):
             assert input_wav_file.getsampwidth() == 2
             assert input_wav_file.getnchannels() == 1
 

pylintrc

@@ -1,3 +1,6 @@
+[MASTER]
+ignored-modules=torch
+
 [MESSAGES CONTROL]
 disable=
   format,
@@ -31,14 +34,7 @@ disable=
   missing-class-docstring,
   missing-function-docstring,
   import-error,
-  consider-using-with
+  relative-beyond-top-level
 
 [FORMAT]
 expected-line-ending-format=LF
-
-[TYPECHECK]
-
-# 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.*

pyproject.toml

@@ -4,41 +4,31 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name        = "piper-sample-generator"
-version     = "3.1.0"
-license     = {text = "Apache-2.0"}
+version     = "3.2.0"
+license     = {text = "MIT"}
 description = "Generate TTS audio samples for training wake word systems"
 readme      = "README.md"
 authors     = [
     {name = "The Home Assistant Authors", email = "hello@home-assistant.io"}
 ]
 keywords    = ["piper", "sample", "tts", "wakeword"]
-classifiers = [
-    "Development Status :: 3 - Alpha",
-    "Intended Audience :: Developers",
-    "Topic :: Text Processing :: Linguistic",
-    "License :: OSI Approved :: Apache Software License",
-    "Programming Language :: Python :: 3.9",
-    "Programming Language :: Python :: 3.10",
-    "Programming Language :: Python :: 3.11",
-    "Programming Language :: Python :: 3.12",
-    "Programming Language :: Python :: 3.13",
-]
 requires-python = ">=3.9.0"
 dependencies = [
-    "piper-tts>=1.3.0,<2",
+    "audiomentations==0.33.0",
+    "piper-tts==1.3.0",
+    "numpy>=2,<3",
     "torch>=2,<3",
     "torchaudio",
-    "audiomentations",
-    "numpy",
+    "webrtcvad",
 ]
 
 [project.optional-dependencies]
 dev = [
-    "black==24.8.0",
-    "flake8==7.2.0",
-    "mypy==1.14.0",
-    "pylint==3.2.7",
-    "pytest==8.3.5",
+    "black==22.12.0",
+    "flake8==6.0.0",
+    "isort==5.11.3",
+    "mypy==0.991",
+    "pylint==2.15.9",
 ]
 
 [project.urls]
@@ -49,4 +39,4 @@ platforms = ["any"]
 zip-safe  = true
 
 [tool.setuptools.packages.find]
-include = []
+include = ["piper_sample_generator*"]

requirements.txt

@@ -1,6 +0,0 @@
-audiomentations==0.33.0
-piper-phonemize==1.1.0
-numpy<2
-torch<2
-torchaudio
-webrtcvad

requirements_dev.txt

@@ -1,5 +0,0 @@
-black==22.12.0
-flake8==6.0.0
-isort==5.11.3
-mypy==0.991
-pylint==2.15.9

script/format

@@ -6,7 +6,7 @@ from pathlib import Path
 _DIR = Path(__file__).parent
 _PROGRAM_DIR = _DIR.parent
 _VENV_DIR = _PROGRAM_DIR / ".venv"
-_SCRIPT = _PROGRAM_DIR / "generate_samples.py"
+_MODULE_DIR = _PROGRAM_DIR / "piper_sample_generator"
 
 if _VENV_DIR.exists():
     context = venv.EnvBuilder().ensure_directories(_VENV_DIR)
@@ -14,5 +14,5 @@ if _VENV_DIR.exists():
 else:
     python_exe = "python3"
 
-subprocess.check_call([python_exe, "-m", "black", str(_SCRIPT)])
-subprocess.check_call([python_exe, "-m", "isort", str(_SCRIPT)])
+subprocess.check_call([python_exe, "-m", "black", str(_MODULE_DIR)])
+subprocess.check_call([python_exe, "-m", "isort", str(_MODULE_DIR)])

script/lint

@@ -6,7 +6,7 @@ from pathlib import Path
 _DIR = Path(__file__).parent
 _PROGRAM_DIR = _DIR.parent
 _VENV_DIR = _PROGRAM_DIR / ".venv"
-_SCRIPT = _PROGRAM_DIR / "generate_samples.py"
+_MODULE_DIR = _PROGRAM_DIR / "piper_sample_generator"
 
 if _VENV_DIR.exists():
     context = venv.EnvBuilder().ensure_directories(_VENV_DIR)
@@ -14,8 +14,8 @@ if _VENV_DIR.exists():
 else:
     python_exe = "python3"
 
-subprocess.check_call([python_exe, "-m", "black", str(_SCRIPT), "--check"])
-subprocess.check_call([python_exe, "-m", "isort", str(_SCRIPT), "--check"])
-subprocess.check_call([python_exe, "-m", "flake8", str(_SCRIPT)])
-subprocess.check_call([python_exe, "-m", "pylint", str(_SCRIPT)])
-subprocess.check_call([python_exe, "-m", "mypy", str(_SCRIPT)])
+subprocess.check_call([python_exe, "-m", "black", str(_MODULE_DIR), "--check"])
+subprocess.check_call([python_exe, "-m", "isort", str(_MODULE_DIR), "--check"])
+subprocess.check_call([python_exe, "-m", "flake8", str(_MODULE_DIR)])
+subprocess.check_call([python_exe, "-m", "pylint", str(_MODULE_DIR)])
+subprocess.check_call([python_exe, "-m", "mypy", str(_MODULE_DIR)])

script/run

@@ -14,4 +14,4 @@ if _VENV_DIR.exists():
 else:
     python_exe = "python3"
 
-subprocess.check_call([python_exe, "generate_samples.py"] + sys.argv[1:])
+subprocess.check_call([python_exe, "-m", "piper_sample_generator"] + sys.argv[1:])