Text-to-Speech
Transformers
Safetensors
English
Hindi
llama
text-generation
tts
hindi
english
audio
speech
india
text-generation-inference
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")# 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
how many voices dose this model has
#7
by oyy-jainil - opened
So open-source models only have 4 voices, right? but in playground there are 11 voices so?
This open-source model has 4 voices. Our self-hosted proprietary model has passed further checkpoints than this one and we are supporting all 10 voices in the playground.
Are you going to release more voices in the open source model?
bharathkumarK changed discussion status to closed