Instructions to use maya-research/Veena with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use maya-research/Veena with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="maya-research/Veena")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("maya-research/Veena") model = AutoModelForCausalLM.from_pretrained("maya-research/Veena", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Real-time streaming support
Any way to achieve streaming of the audios for real-time usecases?
+1
Any way to achieve streaming of the audios for real-time usecases?
If it's for isolated cases, I've a simple server where you can make API calls to generate/synthesise audio files.
I can make it available for online access, but the caveat is that due to resource limitations, it won't be that fast. Should I share that?
Any way to achieve streaming of the audios for real-time usecases?
If it's for isolated cases, I've a simple server where you can make API calls to generate/synthesise audio files.
I can make it available for online access, but the caveat is that due to resource limitations, it won't be that fast. Should I share that?
Sure. Please.