Text-to-Speech
VoxCPM
Laz
Turkish
tts
speech-synthesis
audio
laz
lazca
lazuri
lora
low-resource
endangered-languages
turkey
mozilla-common-voice
Instructions to use Anadilorg/MozilLaz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- VoxCPM
How to use Anadilorg/MozilLaz with VoxCPM:
import soundfile as sf from voxcpm import VoxCPM model = VoxCPM.from_pretrained("Anadilorg/MozilLaz") wav = model.generate( text="VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech.", prompt_wav_path=None, # optional: path to a prompt speech for voice cloning prompt_text=None, # optional: reference text cfg_value=2.0, # LM guidance on LocDiT, higher for better adherence to the prompt, but maybe worse inference_timesteps=10, # LocDiT inference timesteps, higher for better result, lower for fast speed normalize=True, # enable external TN tool denoise=True, # enable external Denoise tool retry_badcase=True, # enable retrying mode for some bad cases (unstoppable) retry_badcase_max_times=3, # maximum retrying times retry_badcase_ratio_threshold=6.0, # maximum length restriction for bad case detection (simple but effective), it could be adjusted for slow pace speech ) sf.write("output.wav", wav, 16000) print("saved: output.wav") - Notebooks
- Google Colab
- Kaggle
| [build-system] | |
| requires = ["setuptools>=61.0"] | |
| build-backend = "setuptools.build_meta" | |
| [project] | |
| name = "mozilaz" | |
| version = "1.0.0" | |
| description = "MozilLaz — Lazca (Lazuri) Text-to-Speech model based on VoxCPM2 + LoRA" | |
| readme = "README.md" | |
| license = {text = "MIT"} | |
| requires-python = ">=3.10" | |
| authors = [ | |
| {name = "MozilLaz Contributors"} | |
| ] | |
| classifiers = [ | |
| "Development Status :: 4 - Beta", | |
| "Intended Audience :: Developers", | |
| "License :: OSI Approved :: MIT License", | |
| "Programming Language :: Python :: 3", | |
| "Programming Language :: Python :: 3.10", | |
| "Programming Language :: Python :: 3.11", | |
| "Programming Language :: Python :: 3.12", | |
| "Topic :: Multimedia :: Sound/Audio :: Speech", | |
| "Topic :: Scientific/Engineering :: Artificial Intelligence", | |
| ] | |
| dependencies = [ | |
| "torch>=2.0", | |
| "torchaudio>=2.0", | |
| "safetensors>=0.3", | |
| "soundfile>=0.11", | |
| "numpy>=1.24", | |
| "voxcpm>=2.0", | |
| ] | |
| [project.optional-dependencies] | |
| demo = ["gradio>=4.0"] | |
| dev = ["pytest", "ruff"] | |
| [project.urls] | |
| Homepage = "https://huggingface.co/Anadilorg/MozilLaz" | |
| Repository = "https://huggingface.co/Anadilorg/MozilLaz" | |
| "Bug Tracker" = "https://huggingface.co/Anadilorg/MozilLaz/discussions" | |
| [tool.setuptools.packages.find] | |
| include = ["mozilaz*"] | |
| exclude = ["*.tests", "*.tests.*"] | |