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.
39 lines
1.2 KiB
Python
39 lines
1.2 KiB
Python
import torch
|
|
from torch.utils.data import Dataset
|
|
import os
|
|
import json
|
|
|
|
from utils.audio_utils import AudioPipeline
|
|
|
|
class LJSpeechDataset(Dataset):
|
|
def __init__(self, root, sample_rate=32000, mode='train'):
|
|
"""
|
|
root: path to LJSpeech-1.1 directory
|
|
"""
|
|
self.root = root
|
|
self.sample_rate = sample_rate
|
|
self.mode = mode
|
|
|
|
mode_json = os.path.join(root, f"{mode}.json")
|
|
if not os.path.exists(mode_json):
|
|
raise FileNotFoundError(f"Dataset JSON not found: {mode_json}")
|
|
|
|
with open(mode_json, 'r') as f:
|
|
self.dataset = json.load(f)
|
|
|
|
def __len__(self):
|
|
return len(self.dataset)
|
|
|
|
def __getitem__(self, idx):
|
|
item = self.dataset[idx]
|
|
text, audio_tokens, wav_path = item
|
|
|
|
# Use the robust OS-aware pipeline to load, convert to mono, and resample
|
|
try:
|
|
wav, _ = AudioPipeline.load_audio(wav_path, target_sr=self.sample_rate)
|
|
except Exception as e:
|
|
print(f"Error loading {wav_path}: {e}")
|
|
# Fallback to 1 second of silence to prevent the dataloader from crashing the entire run
|
|
wav = torch.zeros((1, self.sample_rate))
|
|
|
|
return wav |