Decision Workspace
oxicuda-audio vs citrinet-rs vs sherpa-onnx
Side-by-side comparison of Rust crates
47
oxicuda-audio
experimentalv0.1.8
Audio/Speech ML architectures for OxiCUDA: Conformer encoder, Wav2Vec2 CNN feature extractor, CTC forward+beam-search, WaveNet dilated stack, SpecAugment, speaker embeddings (x-vector/TDNN) — pure Rust, zero CUDA SDK dependency.
49
citrinet-rs
experimentalv0.1.1
Minimal Citrinet speech-to-text inference using ONNX Runtime and kaldi-native-fbank in Rust.
66
sherpa-onnx
experimentalv1.13.2
Safe Rust wrapper for sherpa-onnx speech recognition toolkit
Core Metrics
| oxicuda-audio | citrinet-rs | sherpa-onnx | |
|---|---|---|---|
| Health Score | 47 | 49 | 66 |
| Total Downloads | 38 | 33 | 20.7K |
| 30d Downloads | 0 | 0 | 12.3K |
| Dependents | 0 | 0 | 36 |
| Releases | 3 | 2 | 25 |
| Last Updated | 4d ago | 37d ago | 12d ago |
| Age | 17d | 4m | 3m |
Health Breakdown
oxicuda-audio
Maintenance
14
Quality
13
Community
6
Popularity
2
Documentation
12
citrinet-rs
Maintenance
15
Quality
13
Community
6
Popularity
2
Documentation
13
sherpa-onnx
Maintenance
19
Quality
19
Community
10
Popularity
5
Documentation
13
Technical Details
| oxicuda-audio | citrinet-rs | sherpa-onnx | |
|---|---|---|---|
| Version | 0.1.8 | 0.1.1 | 1.13.2 |
| Stable (≥1.0) | ✗ No | ✗ No | ✓ Yes |
| License | Apache-2.0 | MIT | Apache-2.0 |
| Dependencies | 2 | 4 | 3 |
| Crate Size | 123KB | 14KB | 46KB |
| Features | 0 | 0 | 3 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2024 | 2024 | 2021 |
| MSRV | 1.85 | — | — |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •sherpa-onnx leads with a health score of 66/100, but none of the options score above 80.
- •oxicuda-audio, citrinet-rs are pre-1.0 — API may change.