airvzxf / airvzxf/voxora

Implement voxora-voxtral engine (Mistral Voxtral ASR via Rust binding)

Chiusa
#46 1 commento 0 reazioni 0 assegnatari Vedi su GitHub
blocked engine enhancement pending-engine phase-7
Lingua principale
Rust
Stelle
0
Fork
1
Merge medio
11m
PR unite (30g)
77

Descrizione

Tracks the planned `voxora-voxtral` engine crate. Per ROADMAP
Phase 7.

## Status

**Blocked on upstream.** Mistral Voxtral (released 2025) has no
Rust binding. The reference implementation is Python (transformers
+ safetensors). A Rust port would either be from scratch, a port
of `transformers` pieces, or a candle-based reimplementation.

## What `voxora-voxtral` will be

A new workspace crate that:

- Implements `voxora_traits::AsrEngine` and
`voxora_engine::EngineAdapter` for Mistral Voxtral.
- Supports `voxora-bridge::EngineFamily::Voxtral`.
- Uses `voxora-hf` for model download.
- Supports `voxora-backend` device selection.

## Upstream blockers

- [Voxtral](https://huggingface.co/mistralai/Voxtral) is published
as safetensors weights. The inference code is in Python
(`transformers` library).
- A candle-based implementation would be the cleanest Rust path
but requires significant work.

## Acceptance

- `voxora-voxtral 0.X.0` published.
- `voxora-bridge::EngineFamily::Voxtral` added.
- Parity test against a real Voxtral checkpoint produces the
expected transcript.

## Out of scope

- Training Voxtral.
- Vision-mode of Voxtral (it can also take images). For now we
target the audio-only ASR use case.

Guida per i contributori

Apri la guida per i contributori

Direzione di ricerca

Start with ROADMAP Phase 7 and inspect the named voxora_traits::AsrEngine, voxora_engine::EngineAdapter, voxora-bridge::EngineFamily, voxora-hf, and voxora-backend interfaces. Research the Python transformers reference and available Rust or candle approaches; done means a published voxora-voxtral 0.X.0, Voxtral bridge support, and a parity test against a real checkpoint.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Valutazione

Stack tecnologico
python, rust
Ambito
machine-learning
Tipo di issue
Funzionalità
Difficoltà
5/5
Tempo stimato
Più di una settimana
Stato di attività
Attiva
Chiarezza
Da chiarire
Idoneità per principianti
25/100

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.