mirror of
https://github.com/Nighthawk42/llm-tts-factory.git
synced 2026-08-30 07:22:27 +00:00
Nighthawk
e7ee43de41
Major framework modernization and quality-of-life improvements: - Centralized Configuration: Replaced scattered, hardcoded hyperparameters and paths across all training/inference scripts with a single, documented `config.yaml` and `config_loader.py`. - OS-Aware Audio Pipeline: Introduced `utils/audio_utils.py` to handle cross-platform audio loading. Automatically routes Windows to a robust `ffmpeg` subprocess to bypass unstable Python audio bindings, while keeping `torchaudio` for Linux. - Dependency Management: Migrated from `requirements.txt` to `uv` with a fully configured `pyproject.toml`. Explicitly targets Python 3.12 and pulls PyTorch `cu128` wheels by default. - Dataset Fixes: Restored the missing `dataset_e2e.py` required for proper STFT/GAN decoder training and updated all dataloaders to utilize the new AudioPipeline. - Documentation & Housekeeping: Overhauled `README.md` with updated workflows, Windows instructions, and `uv` setup. Added a comprehensive `.gitignore` for virtual environments, model weights, and cache files.
35 lines
732 B
TOML
35 lines
732 B
TOML
[project]
|
|
name = "llm-tts-factory"
|
|
version = "0.1.0"
|
|
description = "End-to-End LLM-Backbone TTS Training Framework"
|
|
readme = "README.md"
|
|
requires-python = ">=3.12"
|
|
dependencies = [
|
|
"einops",
|
|
"huggingface-hub",
|
|
"matplotlib",
|
|
"numpy",
|
|
"pyyaml",
|
|
"safetensors",
|
|
"scipy",
|
|
"soundfile",
|
|
"torch",
|
|
"torchaudio",
|
|
"tqdm",
|
|
"transformers",
|
|
"wandb",
|
|
]
|
|
|
|
[tool.uv]
|
|
# Tells uv this is an application/scripts directory, not a library to be built
|
|
package = false
|
|
|
|
[tool.uv.sources]
|
|
# Explicitly pull these from the custom PyTorch index
|
|
torch = { index = "pytorch" }
|
|
torchaudio = { index = "pytorch" }
|
|
|
|
[[tool.uv.index]]
|
|
name = "pytorch"
|
|
url = "https://download.pytorch.org/whl/cu128"
|
|
explicit = true |