Reza2kn/Shenava-Rizeh-0.9-onnx-fp16
ONNX FP16 export of Reza2kn/Shenava-Rizeh-0.9 for VisualEars browser/WebGPU inference.
Runtime Contract
- Input
processed_signal:float16, shape[batch, 80, 2005] - Input
processed_signal_length:int64, shape[batch] - Output
logits:float16 - Output
encoded_lengths:int64 - Streaming attention context:
[70, 1] - Tokenizer: SentencePiece BPE, 1024 tokens plus CTC blank
Validation
Parity smoke on the VisualEars 269 benchmark slice:
40/40 exact transcript matches, 1.000000 frame argmax agreement, 0.950 non-empty ONNX rate.
The comparison is source NeMo fp32 encoder plus auxiliary CTC head versus exported ONNX FP16 using the same preprocessed features.
Files
shenava_rizeh_0_9_ctc_fixed2005_len_att70_1_fp16_full_io.onnxβ 6,171,937 bytes β sha256114ba96038eb45d92f449fcc5fdbf67e4c09aa96cbc5b4a4fddb77a52e09df9eshenava_rizeh_0_9_ctc_fixed2005_len_att70_1_fp16_full_io.onnx.dataβ 52,731,906 bytes β sha2563261ed46ccef096a213e29c10f4f7a7a629c2a5895412003ada4db0c1fa9940fshenava_rizeh_0_9_ctc_fixed2005_len_att70_1_fp16_full_io_embedded.onnxβ 58,875,455 bytes β sha2567490c7d364f869912c57c1d57f8ee8688fa284af1305ff8d333ac69c65a74c25tokens.jsonβ 15,115 bytes β sha256895dc224c2b726fa988bdb9f4bd61a5334d594d9f37174399a2f97e68cad91ffpreprocessor.jsonβ 1,795 bytes β sha256b08dcbb46aa54e4414c55306571530b05730b9df0472f7a13a6bcce19cdfaa61mel_filters_slaney_80x257.jsonβ 91,115 bytes β sha256327ad485dfcf1cbd9405ea6512aa0a788990a5c98ef14ba8585896cdc9749866
Generated at 2026-06-23T02:04:27Z.
Model tree for Reza2kn/Shenava-Rizeh-0.9-onnx-fp16
Finetuned
Reza2kn/Shenava-Rizeh-0.9