ABOUT THIS MODEL

Indic multilingual speech recognition with frozen Whisper encoder and language-specific LoRA experts. Supports Hindi, Tamil, Telugu, Bengali, and Marathi with 20× hallucination reduction. ONNX quantized for edge deployment.

KEY HIGHLIGHTS
  • ✓20× reduction in ASR hallucination on Indic languages
  • ✓Frozen encoder preserves multilingual generality
  • ✓ONNX quantised for edge and mobile deployment
  • ✓Handles Hinglish code-switching natively
SPECIFICATIONS
BaseWhisper-Small (frozen)
AdaptersDual LoRA Experts
Router33K parameter selector
LanguagesHindi · Tamil · Telugu · Bengali · Marathi
FormatONNX · HuggingFace
LicenseApache 2.0
Downloads157+
ACADEMIC & RESEARCH CITATION

Cite this Model & Architecture

If you utilize PolyWhisper in your academic research, benchmarks, or enterprise deployments, please cite our open-weight publication:

@misc{eulogik2026polywhisper,
  title        = {PolyWhisper v1.0: Indic Multilingual Speech Recognition},
  author       = {Kishore, Gautam and Eulogik Systems Engineering},
  year         = {2026},
  publisher    = {Eulogik},
  howpublished = {\url{https://eulogik.com/models/polywhisper}}
}

Need help deploying PolyWhisper?

We offer consulting, custom fine-tuning, and on-premise deployment for all our models.