Instructions to use Marvis-AI/marvis-tts-100m-v0.2-MLX-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Marvis-AI/marvis-tts-100m-v0.2-MLX-6bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="Marvis-AI/marvis-tts-100m-v0.2-MLX-6bit")# Load model directly from transformers import AutoProcessor, AutoModelForTextToWaveform processor = AutoProcessor.from_pretrained("Marvis-AI/marvis-tts-100m-v0.2-MLX-6bit") model = AutoModelForTextToWaveform.from_pretrained("Marvis-AI/marvis-tts-100m-v0.2-MLX-6bit", device_map="auto") - MLX
How to use Marvis-AI/marvis-tts-100m-v0.2-MLX-6bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir marvis-tts-100m-v0.2-MLX-6bit Marvis-AI/marvis-tts-100m-v0.2-MLX-6bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download prompts/conversational_b.wav from Marvis-AI/marvis-tts-100m-v0.2-MLX-6bit: direct link, hf CLI and curl.
- Browser
- Download file 636 kB
-
https://huggingface.co/Marvis-AI/marvis-tts-100m-v0.2-MLX-6bit/resolve/main/prompts/conversational_b.wav
- Command line
-
hf download hf://Marvis-AI/marvis-tts-100m-v0.2-MLX-6bit/prompts/conversational_b.wav
-
curl -L -o conversational_b.wav https://huggingface.co/Marvis-AI/marvis-tts-100m-v0.2-MLX-6bit/resolve/main/prompts/conversational_b.wav
636 kB
- Xet hash:
- 88d720797fddc31708aef482d8f0ed8086e0b29e6eaf8a1574a4f0fbc6d74880
- Size of remote file:
- 636 kB
- SHA256:
- 478de94e01ee64b69b4865d6b64540c5840bb2aca9513ececca379a8cd633532
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.