handy-computer/transcribe.cpp
ggml speech-to-text inference for 16+ model families
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
5 releases in the last 90 days, the latest 7 days ago, with 15 contributors on GitHub.
Use Cases & Benefits
- Provides a C/C++ speech-to-text inference library supporting 16+ model families via GGUF models on the ggml runtime with GPU and CPU acceleration.
- Enables fast, numerically verified, and WER-tested speech-to-text transcription across diverse models with multiple hardware backend support for broad compatibility.
- Use for integrating efficient, multi-model speech-to-text transcription in embedded or desktop C++ applications requiring GPU or CPU inference.
- Use for building cross-platform command-line tools or services that transcribe audio streams or batch audio files with high accuracy and low latency.
- Use for developing language bindings in Python, TypeScript, Rust, or Swift to add speech recognition capabilities to web, mobile, or server applications.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
MIT
Permissive: commercial use, modification and redistribution are allowed with attribution.
Community files
- README: present
- Contributing guide: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
C/C++ speech-to-text inference library. Runs diverse STT model families via GGUF models on the ggml runtime, with Metal, Vulkan, and CUDA backends for fast GPU inference plus a tinyBLAS-accelerated CPU path.
16 model families and 60+ variants, streaming and batch. Every model we publish under
handy-computeris numerically verified and WER-tested against its reference implementationPer-variant model cards live under
docs/models/.Metal is enabled automatically on Apple Silicon. For Vulkan (Linux/Windows):
On Windows, see the complete build guide for Vulkan SDK setup, Visual Studio commands, and the short-build-root fallback for unusually deep checkouts.
libopenblas-devis optional but recommended. It accelerates the host-side decoder ~10-15x. Without it the build falls back to a scalar path automatically.tinyBLAS (Justine Tunney's
llamafile_sgemmkernels) is on by default.Pre-built GGUFs for all supported models are hosted on Hugging Face under
handy-computer. Each per-model doc (linked in the table above) includes direct download links for every quant. Convert from source only if you need a different dtype or a checkpoint that isn't pre-built.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
138+70
Open issues
54+15
Compared with peers in Developer Tools
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| stablyai/orca | 116.8K | +6.6K | 40 | today |
| affaan-m/ECC | 297.9K | +5.2K | 63 | 35 days ago |
| DietrichGebert/ponytail | 185.3K | +5.1K | 60 | 7 days ago |
| herdrdev/herdr | 48.3K | +1.7K | 59 | 22 days ago |
| The-PR-Agent/pr-agent | 15.1K | +1.5K | 64 | 11 days ago |
| handy-computer/transcribe.cpp | 2.1K | — | 44 | 7 days ago |
| Category median | 116.8K | +5.1K | 60 | — |
Discover Repositories
Search across tracked repositories by name or description