SchlottAndAI/nemotron-3.5-asr-onnx

Nemotron 3.5 ASR — multilingual one-shot ONNX (fp32, CPU)

An offline, full-context ONNX export of nvidia/nemotron-3.5-asr-streaming-0.6b (FastConformer encoder + RNN-Transducer decoder, ~600M parameters, 40 language-locales) for one-shot (whole-file) transcription on the CPU execution provider.

Produced and consumed by the Cadmus local speech-to-text library. Licensed under OpenMDW-1.1 — see LICENSE and NOTICE (both MUST travel with any redistribution).

Files

File	Purpose
manifest.json	Self-describing model manifest (schema v2) — the content-detection key and the tensor-I/O + feature + language binding
encoder.onnx + encoder.onnx.data	FastConformer encoder with bundled language conditioning; weights in the external .data sidecar (loaded automatically by ONNX Runtime)
decoder_joint.onnx	Fused RNNT prediction network + joint network (one greedy step)
tokens.txt	SentencePiece id→piece map (one piece per line; the decoder's output id space)
tokenizer.model	SentencePiece model (provenance)

A loadable model directory is: manifest.json, encoder.onnx, encoder.onnx.data, decoder_joint.onnx, tokens.txt.

How Cadmus consumes it

Cadmus detects an ONNX Nemotron model by directory content (manifest.json with format == "onnx", schema_version == 2) and routes it to its ONNX engine. The pipeline is: pure-Rust log-mel features (normalize: "NA", raw log-mel) → encoder (x, x_len, prompt_index) → greedy RNNT loop over decoder_joint.

Language is required on this path. The caller supplies a language key; Cadmus maps it through manifest.json → language.map to the encoder's int64 prompt_index. A missing or unknown language surfaces InvalidArgument. Automatic language detection (the model's prompt_index = 101) is intentionally not exposed here.

Languages

120 keys (locale forms such as en-US, de-DE, fr-FR, ja-JP, plus bare forms en, de, fr, …) across 40 language-locales. The full key→id map is in manifest.json → language.map. Examples:

en / en-US → 0      fr / fr-FR → 8      ru / ru-RU → 11
es-ES      → 2      de / de-DE → 9      it / it-IT → 15
zh-CN      → 4      ja / ja-JP → 10     ko / ko-KR → 14