Instructions to use bharatgenai/sooktam2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bharatgenai/sooktam2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="bharatgenai/sooktam2", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("bharatgenai/sooktam2", trust_remote_code=True, device_map="auto") - F5-TTS
How to use bharatgenai/sooktam2 with F5-TTS:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Sooktam2 and Indicf5 model are same ? 😐🙄
This model, BharatGenAI/Sooktam2, feels exactly the same as IndicF5. It honestly looks like the same model has just been rebranded with a different name. There is no noticeable difference in output — voice, tone, speed, narration, and even emotions are completely identical. If this is supposed to be a “new model” with new voices, then where are the changes? Because right now, it gives 100% the same output as IndicF5. It doesn’t even feel like a 0.1% improvement.
Hi @Deathgod7890 , thanks for taking the time to evaluate Sooktam2.
We understand the comparison with IndicF5, but Sooktam2 is a distinct model with a different training methodology and text representation to support cross-lingual adaptability. We're working on publishing more detailed technical documentation to make these distinctions clearer. In the meantime, if you have specific test cases where the outputs feel identical, we'd love to take a look. This kind of feedback helps us improve. You can reach out at contact@bharatgen.com
Thanks again.
-Team BharatGen.