Modelpublic

YUGOROU/Chatterbox-Multilingual-MLX-4bit

sourceHugging Faceupdated 9mo agoView on Hugging Face

4likes125downloads

Model Card

🚨モデルの完全な動作確認がまだできていません！ (🚨We're still working on fully testing the model!)

YUGOROU/Chatterbox-Multilingual-MLX-4bit

Chatterbox Multilingual TTS converted to MLX format for Apple Silicon devices.

🌍 Supported Languages (23 languages)

Arabic, Danish, German, Greek, English, Spanish, Finnish, French, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese, Russian, Swedish, Swahili, Turkish, Chinese

📥 Installation

bash

pip install -U mlx-audio-plus

🚀 Usage

Command Line

bash

mlx_audio.tts.generate \\
    --model {model_name} \\
    --text "こんにちは、元気ですか？" \\
    --ref_audio reference.wav

Python

python

from mlx_audio.tts.generate import generate_audio

generate_audio(
    text="こんにちは、元気ですか？",
    model="{model_name}",
    ref_audio="reference.wav",
    file_prefix="output",
)

📊 Model Details

—Base Model: ResembleAI/chatterbox
—Tokenizer: 2454 tokens (Multilingual)
—Quantization: {'4-bit' if '4bit' in modelname else '8-bit' if '8bit' in modelname else 'fp16'}
—Framework: MLX (Apple Silicon optimized)

🔗 Related

—Original PyTorch model: ResembleAI/chatterbox
—S3Tokenizer: mlx-community/S3TokenizerV2