OpenVINO NPU
Collection
Models specifically tested on Intel's NPU with OpenVINO
•
16 items
•
Updated
•
1
Parakeet TDT 1.1B V3 - OpenVINO
OpenVINO-optimized version of NVIDIA's Parakeet TDT 1.1B V3 model for high-performance multilingual automatic speech recognition on Intel NPUs and CPUs.
Benchmark Results
Hardware: Intel Core Ultra 7 155H (Meteor Lake) with Intel AI Boost NPU Software: OpenVINO 2025.x
LibriSpeech test-clean (English)
| Metric | Value |
|---|---|
| Average WER | 3.7% |
| Median WER | 0.0% |
| Average CER | 1.9% |
| RTFx (NPU) | 25.7× |
| RTFx (CPU) | 5-8× |
| Files processed | 2,620 (5.4 hours) |
FLEURS Multilingual (24 Languages)
| Metric | Value |
|---|---|
| Average WER | 17.0% |
| Average CER | 5.4% |
| Average RTFx | 41.1× |
| Total samples | ~15,000+ |
Best performing languages (WER): Italian 4.3%, Spanish 5.4%, English 6.1%, German 7.4%, French 7.7%
See BENCHMARK_RESULTS.md for complete per-language results.
Performance Comparison
| Implementation | Device | RTFx (Avg) | WER (LibriSpeech) |
|---|---|---|---|
| eddy (OpenVINO) | Intel Core Ultra 7 155H NPU | 25.7× | 3.7% |
| Parakeet (PyTorch) | Intel Arc 140V GPU | ~20×* | ~2.5%* |
| eddy (OpenVINO) | Intel Core Ultra 7 155H CPU | 5-8× | 3.7% |
Note: Benchmarked on HP EliteBook Ultra G1i. eddy NPU is ~1.3× faster than PyTorch on Intel Arc GPU, with lower power consumption. *V3 estimated from V2 benchmark.
Supported Languages
24 European languages: English, Spanish, Italian, French, German, Dutch, Russian, Polish, Ukrainian, Slovak, Bulgarian, Finnish, Romanian, Croatian, Czech, Swedish, Estonian, Hungarian, Lithuanian, Danish, Maltese, Slovenian, Latvian, Greek
Usage
Python usage via ctypes available - see eddy repository for details.
Model Details
- Parameters: 1.1B
- Architecture: FastConformer-RNNT (4-model pipeline)
- Languages: 24 European languages
- Blank token ID: 8192
- Context window: 10s chunks with 3s overlap
- Features: LSTM state continuity, token deduplication, per-token timestamps
License
CC-BY-4.0 - See LICENSE for details.
Links
- GitHub: FluidInference/eddy
- Base Model: nvidia/parakeet-tdt-1.1b
- Documentation: Benchmark Results
Acknowledgments
Based on NVIDIA's Parakeet TDT model. OpenVINO conversion and optimization by the FluidInference team.
- Downloads last month
- 22
Model tree for FluidInference/parakeet-tdt-0.6b-v3-ov
Base model
nvidia/parakeet-tdt-1.1b