juti-ai/typhoon-asr-realtime-onnx

automatic-speech-recognition model by juti-ai

Open original source ↗

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

This is typhoon-ai/typhoon-asr-realtime by SCB 10X (Typhoon), converted from its .nemo release to ONNX for sherpa-onnx. It is a 115M-parameter FastConformer-Transducer for Thai speech recognition, quantized to int8 here (138 MB in total). The Juti app uses it to transcribe Thai speech on the user's computer, offline. The model and its weights are SCB 10X's, licensed CC BY 4.0 (the same license as the original). The only changes are the conversion to ONNX and int8 quantization; the model was not retrained. silerovad.onnx is Silero VAD (MIT license), as distributed by sherpa-onnx. It is included here to cut long recordings at their pauses. The official .nemo (sha-256 d3b731545a0a5cc9841e6b0fcb54cc87a38feae30cb987bb279a57b6734cbce2) was exported with sherpa-onnx's NeMo transducer export (encoder.export, decoder.export, joint.export, metadata…

juti-ai/typhoon-asr-realtime-onnx on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-17T08:00:12.311Z

Inside the original model card — Document outline
  1. Typhoon ASR Real-Time — ONNX (int8) for sherpa-onnx
  2. Files
  3. Use (sherpa-onnx, Python)
  4. How it was made
  5. Accuracy check (character error rate, 100 clips each)
  6. Credit

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Documentation belongs to its respective authors. Reported project/model license: cc-by-4.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

juti-ai/typhoon-asr-realtime-onnx is a automatic-speech-recognition model repository published by juti-ai on Hugging Face. The source reports the sherpa-onnx library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
automatic-speech-recognition
Library
sherpa-onnx
Recent downloads (30 days)
0
Cumulative likes
0
Hugging Face trending score
0
Reported safetensors parameters
Not reported
Architecture
Not reported
License
cc-by-4.0
Access
Not gated by Hugging Face
Created
2026-11-17T06:39:58.000Z
Last modified
2026-11-17T06:43:00.000Z

Compatibility and lineage

Reported languages: th

Reported base models: typhoon-ai/typhoon-asr-realtime

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-11-17T07:01:06.441Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models

argmaxinc/whisperkit-coreml

jonatasgrosman/wav2vec2-large-xlsr-53-japanese

pyannote/speaker-diarization-3.1

Systran/faster-whisper-small

openai/whisper-base

pyannote/speaker-diarization-community-1