betterflow โ€” Hindi/Hinglish streaming CTC (sherpa-onnx)

Streaming zipformer2 CTC exported to ONNX for on-device dictation. Emits partials DURING speech, so first-partial latency is constant (~155 ms class) rather than proportional to utterance length โ€” the property batch whisper structurally lacks.

  • encoder.int8.onnx (69 MB) + tokens.txt (104 Devanagari codepoint tokens)
  • Load with sherpa-onnx
  • Source weights: Vengadanathan/hindi-hinglish-zipformer-ctc-streaming Phase 3 (~337h), Apache-2.0. 25.7% WER IndicVoices-hi / 39.9% Hinglish calls.
  • Exported + int8-quantized + verified decoding real MUCS Hinglish via sherpa-onnx 1.13.4. Casing is a non-issue: Devanagari has no case.

Mirrored so betterflow can pin an immutable revision and checksum. Weights unmodified but for int8 quantization.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support