Instructions to use ai4bharat/indic-seamless with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ai4bharat/indic-seamless with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ai4bharat/indic-seamless")# Load model directly from transformers import AutoTokenizer, AutoModelForSpeechSeq2Seq tokenizer = AutoTokenizer.from_pretrained("ai4bharat/indic-seamless") model = AutoModelForSpeechSeq2Seq.from_pretrained("ai4bharat/indic-seamless") - Notebooks
- Google Colab
- Kaggle
Between Indic-Conformer, IndicF5 and Indic-Seamless - which one should I use for latest TTS
#4
by akshaymishra14 - opened
Apologies if I have not understood the difference or if I am mixing them up but I am confused on which Indic TTS model to pick for my task - Indic Conformer (officially listed on AI4Bharat's page) or Indic F5 - latest model here or Indic Seamless ?
What are the similarities and differences or use cases ?