Nemotron 3 Nano Omni — Chinese ASR/OCR support and speaker diarization for long-form dialogue

AI & Data Science NVIDIA Nemotron
,
1

Background

I’m building a private, on-premise knowledge base (RAG) on a DGX Spark (GB10, ARM64, 128GB unified memory). The corpus is Traditional and Simplified Chinese, and consists of:

  • Hypnotherapy session recordings — 2 to 4 hours each, two-speaker dialogue (practitioner and client)
  • Scanned Chinese PDFs requiring OCR (long-form body text, not forms or tables)

Nano Omni looks attractive because it collapses vision + ASR + LLM into a single model, which matters on a single-GPU edge box. Before investing in the integration work, I need to confirm four things.

1. Chinese speech transcription

Does Nano Omni support Chinese transcription? The Parakeet-TDT-0.6B-v2 audio encoder appears to be English-oriented in its original release, so I’d like to confirm rather than assume.

Specifically: are there measured WER figures for Mandarin Chinese, and are Traditional and Simplified handled differently in the output? My corpus is mixed — some material is Traditional, some Simplified.

2. Chinese OCR

How accurate is Nano Omni’s OCR on Traditional Chinese scanned documents? My use case is long-form body text in scanned PDFs — not tables, forms, or charts. Some documents have no text layer at all.

Is there a benchmark for Chinese OCR specifically, or are the OCRBenchV2 results primarily English?

3. If Chinese is not supported by Omni

I’ve seen Nemotron 3.5 ASR described as covering 40 language-locales, with a caveat that not all 40 are equally production-ready. Where does Mandarin Chinese sit in that list? Is there a published tiering of which locales are production-ready?

If the recommended path is Omni for OCR plus a separate ASR model for Chinese speech, I’d rather know that up front.

4. Speaker diarization

Does Nano Omni provide speaker diarization, or does transcription return an undifferentiated text stream?

This one is decisive for my use case: the entire structure of a therapy session transcript is who is speaking. A transcript that doesn’t distinguish practitioner from client loses most of its value for a knowledge base, and it isn’t recoverable after the fact.

I understand the Parakeet encoder produces word-level timestamps. Is there a supported way to combine those with a diarization step, or a recommended model to pair it with?

Any pointers to existing threads or benchmarks would be welcome — I may be asking something already answered.

2

Audio for this model now runs locally on the Spark. I wrote the
Parakeet/FastConformer audio graph (and the video path) for llama.cpp and
released tested GGUFs plus prebuilt arm64 CUDA binaries here:

Speech transcription and audio reasoning work. I have not tested Chinese ASR
or speaker diarization, so I cannot speak to those yet, but if you try either
on the GGUFs I would be interested in the results.