Shenava v4 β€” FastConformer-115M CTC β€” fp16 ONNX (in-browser / on-device)

fp16 ONNX export of the CTC head of Reza2kn/shenava-fa-fastconformer-115m, for onnxruntime-web (WebGPU / WASM) and onnxruntime. Powers the offline Persian captioner at VisualEars.com.

  • Input: processed_signal float32 [1, 80, 2005] β€” 80-dim log-mel features over a fixed 20.05 s window (NeMo FastConformer preprocessor; configs 115m_preprocessor.json + 115m_mel_filters.json included).
  • Outputs: logits [1, 251, 1025] (CTC, blank id 1024) and encoded_lengths. Greedy-CTC decode with 115m_tokens.json; truncate logits to ceil(real_mel_frames / 8) before collapse.
  • Golden6669 WER: 7.92% (CTC, official Persian normalizer). The parent's RNNT head scores 7.29%.
  • Streaming: the deployed app streams by full-context re-decode of a growing buffer β€” zero accuracy penalty.

Fully offline, on-device. Part of the VisualEars project (SLT 2026).

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. πŸ™‹ Ask for provider support

Model tree for Reza2kn/shenava-fa-fastconformer-115m-onnx-fp16

Quantized
(2)
this model