Decision Workspace
oxicuda-audio vs voxr vs citrinet-rs
Side-by-side comparison of Rust crates
52
oxicuda-audio
experimentalv0.5.5
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.
48
voxr
experimentalv0.1.0
Audio and speech: codecs, DSP, G2P, voices, and TTS/ASR pipelines over boostr models
43
citrinet-rs
experimentalv0.1.1
Minimal Citrinet speech-to-text inference using ONNX Runtime and kaldi-native-fbank in Rust.
Core Metrics
| oxicuda-audio | voxr | citrinet-rs | |
|---|---|---|---|
| Health Score | 52 | 48 | 43 |
| Total Downloads | 226 | 12 | 51 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 1 | 0 |
| Releases | 13 | 1 | 2 |
| Last Updated | 57d ago | today | 174d ago |
| Age | 5m | 1d | 8m |
Health Breakdown
oxicuda-audio
Maintenance
17
Quality
14
Community
6
Popularity
3
Documentation
12
voxr
Maintenance
13
Quality
12
Community
7
Popularity
1
Documentation
15
citrinet-rs
Maintenance
9
Quality
13
Community
6
Popularity
2
Documentation
13
Technical Details
| oxicuda-audio | voxr | citrinet-rs | |
|---|---|---|---|
| Version | 0.5.5 | 0.1.0 | 0.1.1 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | Apache-2.0 | Apache-2.0 | MIT |
| Dependencies | 2 | 20 | 4 |
| Crate Size | 281KB | 3.3MB | 14KB |
| Features | 1 | 16 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2024 | 2024 | 2024 |
| MSRV | 1.85 | 1.95 | — |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •oxicuda-audio leads with a health score of 52/100, but none of the options score above 80.