voxtral.c
Pure C inference of Mistral Voxtral Realtime 4B speech to text model
About
This is a C implementation of the inference pipeline for the Mistral AI's Voxtral Realtime 4B model. It has zero external dependencies beyond the C standard library. The MPS inference is decently fast, while the BLAS acceleration is usable but slow (it continuously convert the bf16 weights to fp32).
Open Source Health
- Stars
- 1,747
- Forks
- 123
- License
- MIT
- Last commit
- 8 months ago
Related Categories
Vendor
Salvatore Sanfilippo
Computer programmer based in Sicily, Italy. I mostly write OSS software. Born 1977. Not a puritan
Quick Links
Open Source
More by Salvatore Sanfilippo
Related Products
Whisper Ctranslate2
Whisper command line client compatible with original OpenAI client based on CTranslate2.
Top category match
Voxtype
Voice-to-text with push-to-talk for Wayland compositors
Top category match
pyVideoTrans
Translate the video from one language to another and embed dubbing & subtitles.
Top category match
Kaldi Gstreamer Server
Real-time full-duplex speech recognition server, based on the Kaldi toolkit and the GStreamer framwork.
Top category match
Vosk Api
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
Top category match