This is the length-aware FA32M CTC acoustic-core export. It fixes the blank-transcript failure from one-input fixed2005 exports by requiring the real valid feature length.

Artifact

Format: ONNX FP16 WebGPU fixed-frame acoustic CTC-core export
Runtime validation: ONNX Runtime CPU
Validation result: 267/269 exact transcript matches (99.26%), argmax step agreement 99.9824%
ONNX non-empty transcript rate: 98.88% on the 269-clip difficult short/noisy set
Size: 116.4 MiB ONNX artifacts

Runtime contract

input: processed_signal float16 [batch, 80, 2005]
input: processed_signal_length int64 [batch] — valid log-mel frame count before zero padding
output: logits float16 [batch, 252, 1025]
output: encoded_lengths int64 [batch]
opset: 18, IR version: 10

Files

File	Bytes	SHA256
`fastconformer_fa32m_ctc_fixed2005_len_fp16_full_io.onnx`	2,892,573	`cd9deee65a201d814fbb42fbe09c1606b0adf479bcd988cc13d764c037762317`
`fastconformer_fa32m_ctc_fixed2005_len_fp16_full_io.onnx.data`	58,170,930	`95aabb839188fe69853e7c2f91970663e2f8ba8560330e087885a359e4db3987`
`fastconformer_fa32m_ctc_fixed2005_len_fp16_full_io_embedded.onnx`	61,036,670	`b51c40efea09b2f3ca6ffaf35341d30c3047e6a9a8d226893037858d86d08473`
`tokens.json`	16,463	`62aa7e4bb7401a1add5459462f3c91378b5177aeaa989a1ba855ad84c3e98500`
`preprocessor.json`	1,909	`988e512147476649c3b7ba865d6916acc4e313d4dc3f7affc7fec3e1a21e789e`
`mel_filters_slaney_80x257.json`	91,115	`327ad485dfcf1cbd9405ea6512aa0a788990a5c98ef14ba8585896cdc9749866`
`parity_smoke20_len.json`	7,871	`5f1f86c643bd6e431bff4d077b99b80f6e84da4e3c611b60145e203b06d1515a`
`parity_full269_len.json`	113,796	`78012aad7f0aea908ba3cf11429f7f56ddadc6ebbf35c3f9cf5e7c5e9500efc4`
`export_manifest.json`	2,868	`18b4e1971c218f8f973926c71384b8291b202ea420e1cb02458bac4d72398d1d`

Validation

Source: PyTorch NeMo preprocessor + encoder + auxiliary CTC decoder in fp32.
Candidate: this ONNX fp16 artifact in ONNX Runtime CPUExecutionProvider.

Validation set: all 269 clips from Reza2kn/visualears-benchmark-269-gold.

json

{
  "created_at_utc": "2026-06-14T23:44:55Z",
  "clips": 269,
  "exact_transcript_matches": 267,
  "exact_transcript_parity": 0.9925650557620818,
  "source_nonempty": 266,
  "onnx_nonempty": 266,
  "onnx_nonempty_rate": 0.9888475836431226,
  "mean_char_similarity": 0.9996047132394416,
  "min_char_similarity": 0.9259259259259259,
  "argmax_step_agreement": 0.9998240520805841,
  "wall_sec": 45.74090790748596,
  "source": "PyTorch NeMo preprocessor + encoder + auxiliary CTC fp32",
  "candidate": "ONNX fp16 encoder + auxiliary CTC with processed_signal_length"
}

Browser / runtime feature contract

Use the sidecars in this repo:

tokens.json — CTC vocabulary and special token ids
preprocessor.json — exact FA32M NeMo fbank contract
mel_filters_slaney_80x257.json — Slaney/librosa mel filters

Feature summary:

preemphasis: y[0]=x[0], y[t]=x[t]-0.97*x[t-1]
STFT: n_fft=512, win_length=400, hop=160, center=True, reflect pad by 256 samples, Hann periodic=false centered inside the FFT frame
spectrum: unnormalized FFT magnitude squared
mel: Slaney/librosa filterbank from the sidecar
log: ln(mel_energy + 2^-24)
no per-bin normalization (normalize=NA)
zero-pad features to 2005 frames and pass the true processed_signal_length
greedy CTC: use encoded_lengths[0], drop blank, repeats, and SentencePiece special tokens like <pad>, <unk>, <fa-IR>

Usage Boundary

These are fixed-frame acoustic CTC-core exports. They take precomputed log-mel features as processed_signal; they are not full raw-audio-to-text pipelines by themselves.

Provenance

Source repo: Reza2kn/visualears-fastconformer-fa32m-streaming-bpe1024
Source file: fa32m_streaming_bpe1024_final.nemo
Source SHA256: 034fb2afa19da13db8a120970a7f8d3e696987014cc62684ce50a1382d332448
Architecture: EncDecHybridRNNTCTCBPEModel encoder + auxiliary CTC decoder with processed_signal_length input

Reza2kn/visualears-fastconformer-fa32m-streaming-bpe1024-onnx-fp16

VisualEars FastConformer FA32M Streaming BPE1024 — ONNX FP16 WebGPU