How to use kenpath/svara-tts-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="kenpath/svara-tts-v1")
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("kenpath/svara-tts-v1") model = AutoModelForCausalLM.from_pretrained("kenpath/svara-tts-v1")
Svara-TTS V1 is a very cool and capable model for indic-tts. I exported the model to ONNX and create a demo space that runs on entirely in browser leveraging WebGPU please let me know if you have any questions.
That's amazing @shreyask , thanks for your contribution :)
Thanks @adityachhabra ! Let me know if you have any feedback on the demo.
· Sign up or log in to comment
