Text-to-Speech
Transformers
Safetensors
llama
text-generation
voice-design
expressive-speech
audio-generation
text-generation-inference
Instructions to use maya-research/maya1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use maya-research/maya1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="maya-research/maya1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("maya-research/maya1") model = AutoModelForCausalLM.from_pretrained("maya-research/maya1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Reproducibility?
#19
by SimonUlander - opened
Is there a way to guarantee that the voice stays constant across clips? Can I fix the seed so that one voice description prompt always produces the same voice?
seed.
Also interested in this for reproducibility between runs. Where would one add this seed parameter to the code templates?