Merge 7a67b709b1 into a5f05418bd

.gitignore

@@ -7,3 +7,4 @@ __pycache__
 /*.egg-info
 /vall_e/version.py
 /build
+/venv

README.md

@@ -6,21 +6,23 @@ An unofficial PyTorch implementation of [VALL-E](https://valle-demo.github.io/),
 
 [!["Buy Me A Coffee"](https://www.buymeacoffee.com/assets/img/custom_images/orange_img.png)](https://www.buymeacoffee.com/enhuiz)
 
-## Install
 
-### Install with pip
+## Installation
 
-```
+Note that the code is only tested under `Python 3.10.7`.
+
+### Install with `pip` (remote)
+```bash
 pip install git+https://github.com/enhuiz/vall-e
 ```
 
-### Clone
+### Install with `pip` (locally)
-
+```bash
-```
 git clone --recurse-submodules https://github.com/enhuiz/vall-e.git
+cd vall-e
+pip install --editable .
 ```
 
-Note that the code is only tested under `Python 3.10.7`.
 
 ## Usage
 
@@ -29,13 +31,13 @@ Note that the code is only tested under `Python 3.10.7`.
 2. Quantize the data:
 
 ```
-python -m vall_e.emb.qnt data/your_data
+valle-quantize data/your_data
 ```
 
 3. Generate phonemes based on the text:
 
 ```
-python -m vall_e.emb.g2p data/your_data
+valle-phonemes data/your_data
 ```
 
 4. Customize your configuration by creating `config/your_data/ar.yml` and `config/your_data/nar.yml`. Refer to the example configs in `config/test` and `vall_e/config.py` for details. You may choose different model presets, check `vall_e/vall_e/__init__.py`.
@@ -43,7 +45,7 @@ python -m vall_e.emb.g2p data/your_data
 5. Train the AR or NAR model using the following scripts:
 
 ```
-python -m vall_e.train yaml=config/your_data/ar_or_nar.yml
+valle-train yaml=config/your_data/ar_or_nar.yml
 ```
 
 ## TODO

pyproject.toml

@@ -0,0 +1,48 @@
+[build-system]
+build-backend = "hatchling.build"
+requires = [
+  "hatchling >= 1.11.0",
+  "pip >= 22.0.0"
+]
+
+[project.scripts]
+valle-quantize = "vall_e.emb.qnt:main"
+valle-phonemes = "vall_e.emb.g2p:main"
+valle-train    = "vall_e.train:main"
+
+
+[project]
+name            = "vall-e"
+version         = "0.0.1"
+description     = "An unofficial toy implementation of the audio LM VALL-E."
+readme          = "README.md"
+license         = "MIT"
+requires-python = ">=3.10"
+
+authors = [
+  { name = "Zhe Niu", email = "niuzhe.nz@outlook.com" },
+]
+
+
+dependencies = [
+  "coloredlogs==15.0.1",
+  "deepspeed==0.7.7",
+  "diskcache==5.4.0",
+  "einops==0.6.0",
+  "encodec==0.1.1",
+  "g2p_en==2.1.0",
+  "humanize==4.4.0",
+  "matplotlib==3.6.0",
+  "numpy==1.23.3",
+  "omegaconf==2.2.3",
+  "openTSNE==0.6.2",
+  "pandas==1.5.0",
+  "soundfile==0.11.0",
+  "torch==1.13.0",
+  "torchaudio==0.13.0",
+  "tqdm==4.64.1",
+]
+
+
+[project.urls]
+GitHub = "https://github.com/enhuiz/vall-e"

requirements.txt

@@ -1,16 +0,0 @@
-coloredlogs==15.0.1
-deepspeed==0.7.7
-diskcache==5.4.0
-einops==0.6.0
-encodec==0.1.1
-g2p_en==2.1.0
-humanize==4.4.0
-matplotlib==3.6.0
-numpy==1.23.3
-omegaconf==2.2.3
-openTSNE==0.6.2
-pandas==1.5.0
-soundfile==0.11.0
-torch==1.13.0+cu116
-torchaudio==0.13.0+cu116
-tqdm==4.64.1

setup.py

@@ -1,59 +0,0 @@
-import subprocess
-from pathlib import Path
-from datetime import datetime
-from setuptools import setup, find_packages
-
-
-def shell(*args):
-    out = subprocess.check_output(args)
-    return out.decode("ascii").strip()
-
-
-def write_version(version_core, pre_release=True):
-    if pre_release:
-        time = shell("git", "log", "-1", "--format=%cd", "--date=iso")
-        time = datetime.strptime(time, "%Y-%m-%d %H:%M:%S %z")
-        time = time.strftime("%Y%m%d%H%M%S")
-        version = f"{version_core}-dev{time}"
-    else:
-        version = version_core
-
-    with open(Path("vall_e", "version.py"), "w") as f:
-        f.write('__version__ = "{}"\n'.format(version))
-
-    return version
-
-
-with open("README.md", "r") as f:
-    long_description = f.read()
-
-setup(
-    name="vall-e",
-    python_requires=">=3.10.0",
-    version=write_version("0.0.1"),
-    description="An unofficial toy implementation of the audio LM VALL-E",
-    author="enhuiz",
-    author_email="niuzhe.nz@outlook.com",
-    long_description=long_description,
-    long_description_content_type="text/markdown",
-    packages=find_packages(),
-    install_requires=[
-        "coloredlogs>=15.0.1",
-        "deepspeed>=0.7.7",
-        "diskcache>=5.4.0",
-        "einops>=0.6.0",
-        "encodec>=0.1.1",
-        "g2p_en>=2.1.0",
-        "humanize>=4.4.0",
-        "matplotlib>=3.6.0",
-        "numpy>=1.23.3",
-        "omegaconf>=2.2.3",
-        "openTSNE>=0.6.2",
-        "pandas>=1.5.0",
-        "soundfile>=0.11.0",
-        "torch>=1.13.0",
-        "torchaudio>=0.13.0",
-        "tqdm>=4.64.1",
-    ],
-    url="https://github.com/enhuiz/vall-e",
-)