indic-conformer-600m-multilingual
- Task
- Speech recognition
- Category
- Audio
- License
- MIT
- Commercial use
- Yes
Permissive license: commercial use is allowed; keep the copyright and license notice. - Size
- About 600 million parameters
- Memory to load
- ~3 GB (estimate)
- Format
- ONNX
- Runs on
- CPU
- Access
- Gated: accept the publisher's terms on Hugging Face
- Downloads (last 30 days)
- 401.3K
- Likes
- 235
- Last updated
- October 8, 2026
How to run it
This is an ONNX export; run it with ONNX Runtime on a CPU or GPU, including in the browser or on mobile.
Plan for roughly 3 GB of memory to load it (our estimate from its size and format).
Downloads are gated: accept the publisher's terms on Hugging Face first.
The model card on Hugging Face has the exact usage code.
Related speech recognition models
Data from Hugging Face's public API, last checked October 19, 2026. Downloads are Hugging Face's count for the last 30 days.