amphion/Emilia-Dataset
Viewer • Updated • 54.8M • 46.9k • 457
How to use Marvis-AI/marvis-tts-250m-v0.1-MLX-4bit with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-to-audio", model="Marvis-AI/marvis-tts-250m-v0.1-MLX-4bit") # Load model directly
from transformers import AutoFeatureExtractor, AutoModelForTextToWaveform
extractor = AutoFeatureExtractor.from_pretrained("Marvis-AI/marvis-tts-250m-v0.1-MLX-4bit")
model = AutoModelForTextToWaveform.from_pretrained("Marvis-AI/marvis-tts-250m-v0.1-MLX-4bit")How to use Marvis-AI/marvis-tts-250m-v0.1-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir marvis-tts-250m-v0.1-MLX-4bit Marvis-AI/marvis-tts-250m-v0.1-MLX-4bit
This model was converted to MLX format from Marvis-AI/marvis-tts-250m-v0.1 using mlx-audio version 0.2.5.
Refer to the original model card for more details on the model.
pip install -U mlx-audio
python -m mlx_audio.tts.generate --model Marvis-AI/marvis-tts-250m-v0.1-MLX-4bit --text "Describe this image."
4-bit
Base model
Marvis-AI/marvis-tts-250m-v0.1-base-pt