QUAN-Transcribe-1.0
QUAN-Transcribe-1.0 is a Vietnamese automatic speech recognition model built on EmbeddingGemma 2. It supports offline transcription and streaming inference.
What it does
Use it to transcribe Vietnamese audio locally, either with full context or in streaming mode.
- Availability
- Publicly accessible repository; accept conditions to access model files and content
- Pricing model
- Not established
- Deployment
- Offline inference
- Privacy
- Can run offline
- Licence
- Gemma Terms of Use
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
6 claims- The model supports Vietnamese speech recognition in offline and streaming modes. [1]
SOTA Fast Vietnamese speech recognition, offline and streaming, built on top of Google's
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - Streaming mode uses 0.48-second chunks. [1]
Streaming support : the same weights decode with full context or in streaming mode (0.48 s chunks).
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model outputs lowercase Vietnamese without punctuation, with numbers written as words. [1]
Output is lowercase Vietnamese without punctuation, with numbers written as words.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The repository is publicly accessible, but users must accept conditions to access its files and content. [1]
This repository is publicly accessible, but you have to accept the conditions to access its files and content .
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model can be run using the provided command-line interface or Python inference code. [1]
- The model is a derivative of EmbeddingGemma 2 and is subject to the Gemma Terms of Use. [1]
This model is a derivative of EmbeddingGemma 2 and is subject to the
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
Sources
1
1
Hugging FaceOwner-controlled
https://huggingface.co/qnguyen3/QUAN-Transcribe-1.0
Retrieved 2026-10-28 00:39 UTC
Verified
Versions
11| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 11 | 2026-10-28 00:39 UTC | material change | deployment, availability, deployment | Current |
| 10 | 2026-10-26 01:48 UTC | material change | capability, deployment, availability, deployment | Current |
| 9 | 2026-10-25 01:44 UTC | material change | capability, availability, deployment | Current |
| 8 | 2026-10-24 02:16 UTC | material change | deployment, availability, deployment | Current |
| 7 | 2026-10-23 02:09 UTC | material change | access, deployment, availability, deployment | Current |
| 6 | 2026-10-22 02:59 UTC | material change | capability, access, availability, deployment | Current |
| 5 | 2026-10-21 03:55 UTC | material change | capability, availability, deployment | Current |
| 4 | 2026-10-20 04:45 UTC | material change | capability, deployment, availability, deployment | Current |
| 3 | 2026-10-19 05:35 UTC | material change | capability, access, deployment, availability, deployment | Current |
| 2 | 2026-10-15 09:21 UTC | material change | availability, privacy | Current |
| 1 | 2026-10-14 10:20 UTC | publication | None | Current |
In briefs
1- Extract structured text from PDFs and images on a CPU Daily brief 2026-10-14
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.
