voicescribe-parakeet

VoiceScribe/voicescribe-parakeet

voicescribe-parakeet is a automatic speech recognition model from VoiceScribe. Use it when you need speech turned into text. The card lists the license as cc-by-4.0.

[](https://discord.gg/WNsvaCtmDe) [](https://github.com/FluidInference/eddy)

Downloads · 30 days

16% of all-time downloads

All-time downloads

Public

Repo size

1.2 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin1.2 GB · 100%

At a glance

Task: Automatic Speech Recognition
License: cc-by-4.0
Access: Public
Created: Apr 23, 2026
Updated: Apr 23, 2026
SHA: 2cf18a95

Base models

nvidia/parakeet-tdt-1.1b

Model card

From the Hugging Face model README

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.

Acknowledgments

Based on NVIDIA's Parakeet TDT model. OpenVINO conversion and optimization by the FluidInference team.

Task: Automatic Speech Recognition
License: cc-by-4.0
Languages: en, es, it, fr, de, nl
Created: Apr 23, 2026
Updated: Apr 23, 2026