gipformer-68M-rnnt

Gipformer - Efficient Vietnamese Speech Recognition

Demo: Try gipformer in your browser

Highlights

• State-of-the-art accuracy — Demonstrates top-tier performance across major Vietnamese ASR benchmarks, delivering highly precise and reliable transcription quality.
• Robust handling of telephonic domains — Excels in processing challenging, noisy real-world call center recordings across all major Vietnamese regional accents.
• Outstanding parameter efficiency — Ranks among the smallest ASR models currently available.
• Seamless edge deployment — Its naturally low resource requirements enable ultra-fast inference on mobile and embedded systems, making it perfectly suited for offline, on-device applications.
• Built-in data privacy — By supporting full local execution, the model ensures sensitive audio data is processed securely on-device, eliminating the need for third-party cloud services.
• gipformer-68M-rnnt is based on Zipformer Transducer architecture.

Benchmark Results

We evaluate gipformer-68M-rnnt against 12 established Vietnamese ASR models across 12 benchmarks spanning call center, medical, broadcast, read speech, etc. All numbers are Word Error Rate (WER %) — lower is better.

Normalization: Both predictions and labels are normalized before computing WER — lowercased, punctuation removed, and numbers converted to spoken form.

Rankings Summary

<details> <summary><b>Dataset Descriptions</b></summary>

Private test sets (call center domain):

• tele-medium — Call center recordings with medium difficulty
• tele-difficult-north — Low-quality call center audio, hard-to-hear speakers — Northern Vietnamese accent
• tele-difficult-middle — Low-quality call center audio, hard-to-hear speakers — Central Vietnamese accent
• tele-difficult-south — Low-quality call center audio, hard-to-hear speakers — Southern Vietnamese accent

Public test sets:

• MultiMED — Multi-domain medical conversations
• VietMed — Vietnamese medical domain
• vlsp-2020-task-1 — VLSP 2020 ASR Shared Task 1
• vlsp-2020-task-2 — VLSP 2020 ASR Shared Task 2
• LSVSC — Large-Scale Vietnamese Speech Corpus
• Fleurs — Google's Few-shot Learning Evaluation of Universal Representations of Speech (Vietnamese subset)
• ViMD — Vietnamese Multi-Domain
• vivos — Vietnamese read speech corpus

</details>

Call Center Domain: Where It Matters Most

Call center ASR is one of the most challenging real-world domains — noisy phone lines, overlapping speech, diverse regional accents, and spontaneous conversation. gipformer-68M-rnnt delivers dominant performance across all call center test sets.

Resources

• Source code: github.com/ggroup-ai-lab/gipformer
• AI Skills: clawhub.ai/ai-ggroup/gipformer

Usage

See the Quick Start guide for detailed usage instructions.

Citation

@misc{gipformer,
  title={Gipformer - Efficient Vietnamese Speech Recognition},
  author={G-Group AI Lab},
  year={2026},
  url={https://huggingface.co/g-group-ai-lab/gipformer-68M-rnnt}
}

License

This model is released under the MIT License.

Acknowledgments

Developed by G-Group AI Lab. For questions, issues, or collaboration inquiries, please visit our HuggingFace organization page.